karrelin commited on
Commit
1e790cc
·
verified ·
1 Parent(s): df07d5b

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. ggml/src/ggml-cpu/CMakeFiles/CMakeDirectoryInformation.cmake +16 -0
  2. ggml/src/ggml-cpu/CMakeFiles/progress.marks +1 -0
  3. ggml/src/ggml-cpu/Makefile +189 -0
  4. ggml/src/ggml-cpu/cmake_install.cmake +50 -0
  5. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/DependInfo.cmake +120 -0
  6. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o +0 -0
  7. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o.d +323 -0
  8. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o +0 -0
  9. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o.d +323 -0
  10. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.o +0 -0
  11. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.o +0 -0
  12. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o.d +323 -0
  13. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o.d +323 -0
  14. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o +0 -0
  15. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o.d +325 -0
  16. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.o +0 -0
  17. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f32.cu.o.d +326 -0
  18. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-wmma-f16.cu.o.d +329 -0
  19. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o.d +325 -0
  20. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gla.cu.o +0 -0
  21. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp +1 -0
  22. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/link.txt +1 -0
  23. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o.d +324 -0
  24. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o.d +327 -0
  25. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o.d +323 -0
  26. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o.d +323 -0
  27. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o.d +323 -0
  28. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/progress.make +100 -0
  29. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o.d +325 -0
  30. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o.d +323 -0
  31. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o.d +1038 -0
  32. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o.d +324 -0
  33. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o.d +328 -0
  34. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o.d +328 -0
  35. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o.d +328 -0
  36. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o.d +328 -0
  37. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o.d +328 -0
  38. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o.d +328 -0
  39. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o.d +328 -0
  40. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o.d +328 -0
  41. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o.d +328 -0
  42. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o.d +328 -0
  43. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o.d +328 -0
  44. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o.d +328 -0
  45. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o.d +328 -0
  46. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o.d +328 -0
  47. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o.d +328 -0
  48. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o.d +328 -0
  49. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o.d +328 -0
  50. ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o.d +328 -0
ggml/src/ggml-cpu/CMakeFiles/CMakeDirectoryInformation.cmake ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # CMAKE generated file: DO NOT EDIT!
2
+ # Generated by "Unix Makefiles" Generator, CMake Version 3.31
3
+
4
+ # Relative path conversion top directories.
5
+ set(CMAKE_RELATIVE_PATH_TOP_SOURCE "/content/tmp")
6
+ set(CMAKE_RELATIVE_PATH_TOP_BINARY "/content/tmp/build")
7
+
8
+ # Force unix paths in dependencies.
9
+ set(CMAKE_FORCE_UNIX_PATHS 1)
10
+
11
+
12
+ # The C and CXX include file regular expressions for this directory.
13
+ set(CMAKE_C_INCLUDE_REGEX_SCAN "^.*$")
14
+ set(CMAKE_C_INCLUDE_REGEX_COMPLAIN "^$")
15
+ set(CMAKE_CXX_INCLUDE_REGEX_SCAN ${CMAKE_C_INCLUDE_REGEX_SCAN})
16
+ set(CMAKE_CXX_INCLUDE_REGEX_COMPLAIN ${CMAKE_C_INCLUDE_REGEX_COMPLAIN})
ggml/src/ggml-cpu/CMakeFiles/progress.marks ADDED
@@ -0,0 +1 @@
 
 
1
+ 0
ggml/src/ggml-cpu/Makefile ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # CMAKE generated file: DO NOT EDIT!
2
+ # Generated by "Unix Makefiles" Generator, CMake Version 3.31
3
+
4
+ # Default target executed when no arguments are given to make.
5
+ default_target: all
6
+ .PHONY : default_target
7
+
8
+ # Allow only one "make -f Makefile2" at a time, but pass parallelism.
9
+ .NOTPARALLEL:
10
+
11
+ #=============================================================================
12
+ # Special targets provided by cmake.
13
+
14
+ # Disable implicit rules so canonical targets will work.
15
+ .SUFFIXES:
16
+
17
+ # Disable VCS-based implicit rules.
18
+ % : %,v
19
+
20
+ # Disable VCS-based implicit rules.
21
+ % : RCS/%
22
+
23
+ # Disable VCS-based implicit rules.
24
+ % : RCS/%,v
25
+
26
+ # Disable VCS-based implicit rules.
27
+ % : SCCS/s.%
28
+
29
+ # Disable VCS-based implicit rules.
30
+ % : s.%
31
+
32
+ .SUFFIXES: .hpux_make_needs_suffix_list
33
+
34
+ # Command-line flag to silence nested $(MAKE).
35
+ $(VERBOSE)MAKESILENT = -s
36
+
37
+ #Suppress display of executed commands.
38
+ $(VERBOSE).SILENT:
39
+
40
+ # A target that is always out of date.
41
+ cmake_force:
42
+ .PHONY : cmake_force
43
+
44
+ #=============================================================================
45
+ # Set environment variables for the build.
46
+
47
+ # The shell in which to execute make rules.
48
+ SHELL = /bin/sh
49
+
50
+ # The CMake executable.
51
+ CMAKE_COMMAND = /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake
52
+
53
+ # The command to remove a file.
54
+ RM = /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -E rm -f
55
+
56
+ # Escaping for special characters.
57
+ EQUALS = =
58
+
59
+ # The top-level source directory on which CMake was run.
60
+ CMAKE_SOURCE_DIR = /content/tmp
61
+
62
+ # The top-level build directory on which CMake was run.
63
+ CMAKE_BINARY_DIR = /content/tmp/build
64
+
65
+ #=============================================================================
66
+ # Targets provided globally by CMake.
67
+
68
+ # Special rule for the target edit_cache
69
+ edit_cache:
70
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "No interactive CMake dialog available..."
71
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -E echo No\ interactive\ CMake\ dialog\ available.
72
+ .PHONY : edit_cache
73
+
74
+ # Special rule for the target edit_cache
75
+ edit_cache/fast: edit_cache
76
+ .PHONY : edit_cache/fast
77
+
78
+ # Special rule for the target rebuild_cache
79
+ rebuild_cache:
80
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Running CMake to regenerate build system..."
81
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake --regenerate-during-build -S$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR)
82
+ .PHONY : rebuild_cache
83
+
84
+ # Special rule for the target rebuild_cache
85
+ rebuild_cache/fast: rebuild_cache
86
+ .PHONY : rebuild_cache/fast
87
+
88
+ # Special rule for the target list_install_components
89
+ list_install_components:
90
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Available install components are: \"Unspecified\""
91
+ .PHONY : list_install_components
92
+
93
+ # Special rule for the target list_install_components
94
+ list_install_components/fast: list_install_components
95
+ .PHONY : list_install_components/fast
96
+
97
+ # Special rule for the target install
98
+ install: preinstall
99
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Install the project..."
100
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -P cmake_install.cmake
101
+ .PHONY : install
102
+
103
+ # Special rule for the target install
104
+ install/fast: preinstall/fast
105
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Install the project..."
106
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -P cmake_install.cmake
107
+ .PHONY : install/fast
108
+
109
+ # Special rule for the target install/local
110
+ install/local: preinstall
111
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Installing only the local directory..."
112
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -DCMAKE_INSTALL_LOCAL_ONLY=1 -P cmake_install.cmake
113
+ .PHONY : install/local
114
+
115
+ # Special rule for the target install/local
116
+ install/local/fast: preinstall/fast
117
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Installing only the local directory..."
118
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -DCMAKE_INSTALL_LOCAL_ONLY=1 -P cmake_install.cmake
119
+ .PHONY : install/local/fast
120
+
121
+ # Special rule for the target install/strip
122
+ install/strip: preinstall
123
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Installing the project stripped..."
124
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -DCMAKE_INSTALL_DO_STRIP=1 -P cmake_install.cmake
125
+ .PHONY : install/strip
126
+
127
+ # Special rule for the target install/strip
128
+ install/strip/fast: preinstall/fast
129
+ @$(CMAKE_COMMAND) -E cmake_echo_color "--switch=$(COLOR)" --cyan "Installing the project stripped..."
130
+ /usr/local/lib/python3.11/dist-packages/cmake/data/bin/cmake -DCMAKE_INSTALL_DO_STRIP=1 -P cmake_install.cmake
131
+ .PHONY : install/strip/fast
132
+
133
+ # The main all target
134
+ all: cmake_check_build_system
135
+ cd /content/tmp/build && $(CMAKE_COMMAND) -E cmake_progress_start /content/tmp/build/CMakeFiles /content/tmp/build/ggml/src/ggml-cpu//CMakeFiles/progress.marks
136
+ cd /content/tmp/build && $(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 ggml/src/ggml-cpu/all
137
+ $(CMAKE_COMMAND) -E cmake_progress_start /content/tmp/build/CMakeFiles 0
138
+ .PHONY : all
139
+
140
+ # The main clean target
141
+ clean:
142
+ cd /content/tmp/build && $(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 ggml/src/ggml-cpu/clean
143
+ .PHONY : clean
144
+
145
+ # The main clean target
146
+ clean/fast: clean
147
+ .PHONY : clean/fast
148
+
149
+ # Prepare targets for installation.
150
+ preinstall: all
151
+ cd /content/tmp/build && $(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 ggml/src/ggml-cpu/preinstall
152
+ .PHONY : preinstall
153
+
154
+ # Prepare targets for installation.
155
+ preinstall/fast:
156
+ cd /content/tmp/build && $(MAKE) $(MAKESILENT) -f CMakeFiles/Makefile2 ggml/src/ggml-cpu/preinstall
157
+ .PHONY : preinstall/fast
158
+
159
+ # clear depends
160
+ depend:
161
+ cd /content/tmp/build && $(CMAKE_COMMAND) -S$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR) --check-build-system CMakeFiles/Makefile.cmake 1
162
+ .PHONY : depend
163
+
164
+ # Help Target
165
+ help:
166
+ @echo "The following are some of the valid targets for this Makefile:"
167
+ @echo "... all (the default if no target is provided)"
168
+ @echo "... clean"
169
+ @echo "... depend"
170
+ @echo "... edit_cache"
171
+ @echo "... install"
172
+ @echo "... install/local"
173
+ @echo "... install/strip"
174
+ @echo "... list_install_components"
175
+ @echo "... rebuild_cache"
176
+ .PHONY : help
177
+
178
+
179
+
180
+ #=============================================================================
181
+ # Special targets to cleanup operation of make.
182
+
183
+ # Special rule to run CMake to check the build system integrity.
184
+ # No rule that depends on this can have commands that come from listfiles
185
+ # because they might be regenerated.
186
+ cmake_check_build_system:
187
+ cd /content/tmp/build && $(CMAKE_COMMAND) -S$(CMAKE_SOURCE_DIR) -B$(CMAKE_BINARY_DIR) --check-build-system CMakeFiles/Makefile.cmake 0
188
+ .PHONY : cmake_check_build_system
189
+
ggml/src/ggml-cpu/cmake_install.cmake ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Install script for directory: /content/tmp/ggml/src/ggml-cpu
2
+
3
+ # Set the install prefix
4
+ if(NOT DEFINED CMAKE_INSTALL_PREFIX)
5
+ set(CMAKE_INSTALL_PREFIX "/usr/local")
6
+ endif()
7
+ string(REGEX REPLACE "/$" "" CMAKE_INSTALL_PREFIX "${CMAKE_INSTALL_PREFIX}")
8
+
9
+ # Set the install configuration name.
10
+ if(NOT DEFINED CMAKE_INSTALL_CONFIG_NAME)
11
+ if(BUILD_TYPE)
12
+ string(REGEX REPLACE "^[^A-Za-z0-9_]+" ""
13
+ CMAKE_INSTALL_CONFIG_NAME "${BUILD_TYPE}")
14
+ else()
15
+ set(CMAKE_INSTALL_CONFIG_NAME "Release")
16
+ endif()
17
+ message(STATUS "Install configuration: \"${CMAKE_INSTALL_CONFIG_NAME}\"")
18
+ endif()
19
+
20
+ # Set the component getting installed.
21
+ if(NOT CMAKE_INSTALL_COMPONENT)
22
+ if(COMPONENT)
23
+ message(STATUS "Install component: \"${COMPONENT}\"")
24
+ set(CMAKE_INSTALL_COMPONENT "${COMPONENT}")
25
+ else()
26
+ set(CMAKE_INSTALL_COMPONENT)
27
+ endif()
28
+ endif()
29
+
30
+ # Install shared libraries without execute permission?
31
+ if(NOT DEFINED CMAKE_INSTALL_SO_NO_EXE)
32
+ set(CMAKE_INSTALL_SO_NO_EXE "1")
33
+ endif()
34
+
35
+ # Is this installation the result of a crosscompile?
36
+ if(NOT DEFINED CMAKE_CROSSCOMPILING)
37
+ set(CMAKE_CROSSCOMPILING "FALSE")
38
+ endif()
39
+
40
+ # Set path to fallback-tool for dependency-resolution.
41
+ if(NOT DEFINED CMAKE_OBJDUMP)
42
+ set(CMAKE_OBJDUMP "/usr/bin/objdump")
43
+ endif()
44
+
45
+ string(REPLACE ";" "\n" CMAKE_INSTALL_MANIFEST_CONTENT
46
+ "${CMAKE_INSTALL_MANIFEST_FILES}")
47
+ if(CMAKE_INSTALL_LOCAL_ONLY)
48
+ file(WRITE "/content/tmp/build/ggml/src/ggml-cpu/install_local_manifest.txt"
49
+ "${CMAKE_INSTALL_MANIFEST_CONTENT}")
50
+ endif()
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/DependInfo.cmake ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # Consider dependencies only in project.
3
+ set(CMAKE_DEPENDS_IN_PROJECT_ONLY OFF)
4
+
5
+ # The set of languages for which implicit dependencies are needed:
6
+ set(CMAKE_DEPENDS_LANGUAGES
7
+ )
8
+
9
+ # The set of dependency files which are needed:
10
+ set(CMAKE_DEPENDS_DEPENDENCY_FILES
11
+ "/content/tmp/ggml/src/ggml-cuda/acc.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o.d"
12
+ "/content/tmp/ggml/src/ggml-cuda/add-id.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o.d"
13
+ "/content/tmp/ggml/src/ggml-cuda/arange.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.o.d"
14
+ "/content/tmp/ggml/src/ggml-cuda/argmax.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argmax.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argmax.cu.o.d"
15
+ "/content/tmp/ggml/src/ggml-cuda/argsort.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.o.d"
16
+ "/content/tmp/ggml/src/ggml-cuda/binbcast.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o.d"
17
+ "/content/tmp/ggml/src/ggml-cuda/clamp.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o.d"
18
+ "/content/tmp/ggml/src/ggml-cuda/concat.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/concat.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/concat.cu.o.d"
19
+ "/content/tmp/ggml/src/ggml-cuda/conv-transpose-1d.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.o.d"
20
+ "/content/tmp/ggml/src/ggml-cuda/conv2d-dw.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o.d"
21
+ "/content/tmp/ggml/src/ggml-cuda/conv2d-transpose.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o.d"
22
+ "/content/tmp/ggml/src/ggml-cuda/convert.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/convert.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/convert.cu.o.d"
23
+ "/content/tmp/ggml/src/ggml-cuda/count-equal.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/count-equal.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/count-equal.cu.o.d"
24
+ "/content/tmp/ggml/src/ggml-cuda/cpy.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cpy.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cpy.cu.o.d"
25
+ "/content/tmp/ggml/src/ggml-cuda/cross-entropy-loss.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.o.d"
26
+ "/content/tmp/ggml/src/ggml-cuda/diagmask.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.o.d"
27
+ "/content/tmp/ggml/src/ggml-cuda/fattn-tile-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f16.cu.o.d"
28
+ "/content/tmp/ggml/src/ggml-cuda/fattn-tile-f32.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f32.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f32.cu.o.d"
29
+ "/content/tmp/ggml/src/ggml-cuda/fattn-wmma-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-wmma-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-wmma-f16.cu.o.d"
30
+ "/content/tmp/ggml/src/ggml-cuda/fattn.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn.cu.o.d"
31
+ "/content/tmp/ggml/src/ggml-cuda/getrows.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o.d"
32
+ "/content/tmp/ggml/src/ggml-cuda/ggml-cuda.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ggml-cuda.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ggml-cuda.cu.o.d"
33
+ "/content/tmp/ggml/src/ggml-cuda/gla.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gla.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gla.cu.o.d"
34
+ "/content/tmp/ggml/src/ggml-cuda/im2col.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/im2col.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/im2col.cu.o.d"
35
+ "/content/tmp/ggml/src/ggml-cuda/mean.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mean.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mean.cu.o.d"
36
+ "/content/tmp/ggml/src/ggml-cuda/mmf.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o.d"
37
+ "/content/tmp/ggml/src/ggml-cuda/mmq.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o.d"
38
+ "/content/tmp/ggml/src/ggml-cuda/mmvf.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvf.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvf.cu.o.d"
39
+ "/content/tmp/ggml/src/ggml-cuda/mmvq.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvq.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvq.cu.o.d"
40
+ "/content/tmp/ggml/src/ggml-cuda/norm.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/norm.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/norm.cu.o.d"
41
+ "/content/tmp/ggml/src/ggml-cuda/opt-step-adamw.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-adamw.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-adamw.cu.o.d"
42
+ "/content/tmp/ggml/src/ggml-cuda/opt-step-sgd.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o.d"
43
+ "/content/tmp/ggml/src/ggml-cuda/out-prod.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o.d"
44
+ "/content/tmp/ggml/src/ggml-cuda/pad.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o.d"
45
+ "/content/tmp/ggml/src/ggml-cuda/pool2d.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pool2d.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pool2d.cu.o.d"
46
+ "/content/tmp/ggml/src/ggml-cuda/quantize.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/quantize.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/quantize.cu.o.d"
47
+ "/content/tmp/ggml/src/ggml-cuda/roll.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/roll.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/roll.cu.o.d"
48
+ "/content/tmp/ggml/src/ggml-cuda/rope.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/rope.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/rope.cu.o.d"
49
+ "/content/tmp/ggml/src/ggml-cuda/scale.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/scale.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/scale.cu.o.d"
50
+ "/content/tmp/ggml/src/ggml-cuda/set-rows.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o.d"
51
+ "/content/tmp/ggml/src/ggml-cuda/softcap.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o.d"
52
+ "/content/tmp/ggml/src/ggml-cuda/softmax.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softmax.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softmax.cu.o.d"
53
+ "/content/tmp/ggml/src/ggml-cuda/ssm-conv.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-conv.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-conv.cu.o.d"
54
+ "/content/tmp/ggml/src/ggml-cuda/ssm-scan.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o.d"
55
+ "/content/tmp/ggml/src/ggml-cuda/sum.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sum.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sum.cu.o.d"
56
+ "/content/tmp/ggml/src/ggml-cuda/sumrows.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o.d"
57
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o.d"
58
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o.d"
59
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o.d"
60
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o.d"
61
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o.d"
62
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o.d"
63
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o.d"
64
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o.d"
65
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o.d"
66
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o.d"
67
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o.d"
68
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o.d"
69
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o.d"
70
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o.d"
71
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o.d"
72
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o.d"
73
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o.d"
74
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o.d"
75
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu.o.d"
76
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu.o.d"
77
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu.o.d"
78
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu.o.d"
79
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu.o.d"
80
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu.o.d"
81
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu.o.d"
82
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu.o.d"
83
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu.o.d"
84
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu.o.d"
85
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu.o.d"
86
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq1_s.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq1_s.cu.o.d"
87
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_s.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_s.cu.o.d"
88
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xs.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xs.cu.o.d"
89
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xxs.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xxs.cu.o.d"
90
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_s.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_s.cu.o.d"
91
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_xxs.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_xxs.cu.o.d"
92
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_nl.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_nl.cu.o.d"
93
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_xs.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_xs.cu.o.d"
94
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-mxfp4.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-mxfp4.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-mxfp4.cu.o.d"
95
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_k.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_k.cu.o.d"
96
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q3_k.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q3_k.cu.o.d"
97
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_0.cu.o.d"
98
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_1.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_1.cu.o.d"
99
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_k.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_k.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_k.cu.o.d"
100
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_0.cu.o.d"
101
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_1.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_1.cu.o.d"
102
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_k.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_k.cu.o.d"
103
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q6_k.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q6_k.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q6_k.cu.o.d"
104
+ "/content/tmp/ggml/src/ggml-cuda/template-instances/mmq-instance-q8_0.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q8_0.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q8_0.cu.o.d"
105
+ "/content/tmp/ggml/src/ggml-cuda/tsembd.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tsembd.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tsembd.cu.o.d"
106
+ "/content/tmp/ggml/src/ggml-cuda/unary.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/unary.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/unary.cu.o.d"
107
+ "/content/tmp/ggml/src/ggml-cuda/upscale.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/upscale.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/upscale.cu.o.d"
108
+ "/content/tmp/ggml/src/ggml-cuda/wkv.cu" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/wkv.cu.o" "gcc" "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/wkv.cu.o.d"
109
+ )
110
+
111
+ # Targets to which this target links which contain Fortran sources.
112
+ set(CMAKE_Fortran_TARGET_LINKED_INFO_FILES
113
+ )
114
+
115
+ # Targets to which this target links which contain Fortran sources.
116
+ set(CMAKE_Fortran_TARGET_FORWARD_LINKED_INFO_FILES
117
+ )
118
+
119
+ # Fortran module output directory.
120
+ set(CMAKE_Fortran_TARGET_MODULE_DIR "")
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o ADDED
Binary file (72.1 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o : /content/tmp/ggml/src/ggml-cuda/acc.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/acc.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o ADDED
Binary file (68.6 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o : /content/tmp/ggml/src/ggml-cuda/add-id.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/add-id.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.o ADDED
Binary file (66.4 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.o ADDED
Binary file (73.1 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o : /content/tmp/ggml/src/ggml-cuda/binbcast.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/binbcast.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o : /content/tmp/ggml/src/ggml-cuda/clamp.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/clamp.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o ADDED
Binary file (87.7 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o.d ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o : /content/tmp/ggml/src/ggml-cuda/conv2d-transpose.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /usr/include/c++/11/algorithm \
229
+ /usr/include/c++/11/pstl/glue_algorithm_defs.h \
230
+ /usr/include/c++/11/pstl/execution_defs.h \
231
+ /content/tmp/ggml/src/ggml-cuda/conv2d-transpose.cuh \
232
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
233
+ /content/tmp/ggml/src/../include/ggml.h \
234
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
235
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
236
+ /usr/include/stdint.h \
237
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
238
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
239
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
240
+ /content/tmp/ggml/src/../include/gguf.h \
241
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
242
+ /content/tmp/ggml/src/../include/ggml-backend.h \
243
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
244
+ /usr/include/c++/11/cstdint \
245
+ /usr/include/c++/11/memory \
246
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
247
+ /usr/include/c++/11/bits/align.h \
248
+ /usr/include/c++/11/bit \
249
+ /usr/include/c++/11/bits/unique_ptr.h \
250
+ /usr/include/c++/11/bits/shared_ptr.h \
251
+ /usr/include/c++/11/iosfwd \
252
+ /usr/include/c++/11/bits/stringfwd.h \
253
+ /usr/include/c++/11/bits/postypes.h \
254
+ /usr/include/c++/11/cwchar \
255
+ /usr/include/wchar.h \
256
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
257
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
258
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
259
+ /usr/include/c++/11/bits/shared_ptr_base.h \
260
+ /usr/include/c++/11/bits/allocated_ptr.h \
261
+ /usr/include/c++/11/ext/atomicity.h \
262
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
263
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
264
+ /usr/include/pthread.h \
265
+ /usr/include/sched.h \
266
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
268
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
269
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
270
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
271
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
272
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
273
+ /usr/include/c++/11/ext/concurrence.h \
274
+ /usr/include/c++/11/exception \
275
+ /usr/include/c++/11/bits/exception_ptr.h \
276
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
277
+ /usr/include/c++/11/bits/nested_exception.h \
278
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
279
+ /usr/include/c++/11/bits/atomic_base.h \
280
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
281
+ /usr/include/c++/11/backward/auto_ptr.h \
282
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
283
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
284
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
286
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
287
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
288
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
289
+ /usr/include/c++/11/cassert \
290
+ /usr/include/c++/11/cfloat \
291
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
292
+ /usr/include/c++/11/cstdio \
293
+ /usr/include/c++/11/string \
294
+ /usr/include/c++/11/bits/char_traits.h \
295
+ /usr/include/c++/11/bits/localefwd.h \
296
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
297
+ /usr/include/c++/11/clocale \
298
+ /usr/include/locale.h \
299
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
300
+ /usr/include/c++/11/cctype \
301
+ /usr/include/c++/11/bits/ostream_insert.h \
302
+ /usr/include/c++/11/bits/cxxabi_forced.h \
303
+ /usr/include/c++/11/bits/basic_string.h \
304
+ /usr/include/c++/11/string_view \
305
+ /usr/include/c++/11/bits/string_view.tcc \
306
+ /usr/include/c++/11/ext/string_conversions.h \
307
+ /usr/include/c++/11/cerrno \
308
+ /usr/include/errno.h \
309
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
310
+ /usr/include/linux/errno.h \
311
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
312
+ /usr/include/asm-generic/errno.h \
313
+ /usr/include/asm-generic/errno-base.h \
314
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
315
+ /usr/include/c++/11/bits/charconv.h \
316
+ /usr/include/c++/11/bits/basic_string.tcc \
317
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
324
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
325
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.o ADDED
Binary file (66.7 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f32.cu.o.d ADDED
@@ -0,0 +1,326 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile-f32.cu.o : /content/tmp/ggml/src/ggml-cuda/fattn-tile-f32.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
229
+ /content/tmp/ggml/src/../include/ggml.h \
230
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
232
+ /usr/include/stdint.h \
233
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
234
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
235
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
236
+ /content/tmp/ggml/src/../include/gguf.h \
237
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
238
+ /content/tmp/ggml/src/../include/ggml-backend.h \
239
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
240
+ /usr/include/c++/11/cstdint \
241
+ /usr/include/c++/11/memory \
242
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
243
+ /usr/include/c++/11/bits/align.h \
244
+ /usr/include/c++/11/bit \
245
+ /usr/include/c++/11/bits/unique_ptr.h \
246
+ /usr/include/c++/11/bits/shared_ptr.h \
247
+ /usr/include/c++/11/iosfwd \
248
+ /usr/include/c++/11/bits/stringfwd.h \
249
+ /usr/include/c++/11/bits/postypes.h \
250
+ /usr/include/c++/11/cwchar \
251
+ /usr/include/wchar.h \
252
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
255
+ /usr/include/c++/11/bits/shared_ptr_base.h \
256
+ /usr/include/c++/11/bits/allocated_ptr.h \
257
+ /usr/include/c++/11/ext/atomicity.h \
258
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
260
+ /usr/include/pthread.h \
261
+ /usr/include/sched.h \
262
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
264
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
265
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
266
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
267
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
268
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
269
+ /usr/include/c++/11/ext/concurrence.h \
270
+ /usr/include/c++/11/exception \
271
+ /usr/include/c++/11/bits/exception_ptr.h \
272
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
273
+ /usr/include/c++/11/bits/nested_exception.h \
274
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
275
+ /usr/include/c++/11/bits/atomic_base.h \
276
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
277
+ /usr/include/c++/11/backward/auto_ptr.h \
278
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
279
+ /usr/include/c++/11/pstl/execution_defs.h \
280
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
281
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
285
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
286
+ /usr/include/c++/11/cassert \
287
+ /usr/include/c++/11/cfloat \
288
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
289
+ /usr/include/c++/11/cstdio \
290
+ /usr/include/c++/11/string \
291
+ /usr/include/c++/11/bits/char_traits.h \
292
+ /usr/include/c++/11/bits/localefwd.h \
293
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
294
+ /usr/include/c++/11/clocale \
295
+ /usr/include/locale.h \
296
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
297
+ /usr/include/c++/11/cctype \
298
+ /usr/include/c++/11/bits/ostream_insert.h \
299
+ /usr/include/c++/11/bits/cxxabi_forced.h \
300
+ /usr/include/c++/11/bits/basic_string.h \
301
+ /usr/include/c++/11/string_view \
302
+ /usr/include/c++/11/bits/string_view.tcc \
303
+ /usr/include/c++/11/ext/string_conversions.h \
304
+ /usr/include/c++/11/cerrno \
305
+ /usr/include/errno.h \
306
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
307
+ /usr/include/linux/errno.h \
308
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
309
+ /usr/include/asm-generic/errno.h \
310
+ /usr/include/asm-generic/errno-base.h \
311
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
312
+ /usr/include/c++/11/bits/charconv.h \
313
+ /usr/include/c++/11/bits/basic_string.tcc \
314
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
315
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
323
+ /content/tmp/ggml/src/ggml-cuda/fattn-common.cuh \
324
+ /content/tmp/ggml/src/ggml-cuda/convert.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/vecdotq.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/fattn-tile-f32.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-wmma-f16.cu.o.d ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-wmma-f16.cu.o : /content/tmp/ggml/src/ggml-cuda/fattn-wmma-f16.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
229
+ /content/tmp/ggml/src/../include/ggml.h \
230
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
232
+ /usr/include/stdint.h \
233
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
234
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
235
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
236
+ /content/tmp/ggml/src/../include/gguf.h \
237
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
238
+ /content/tmp/ggml/src/../include/ggml-backend.h \
239
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
240
+ /usr/include/c++/11/cstdint \
241
+ /usr/include/c++/11/memory \
242
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
243
+ /usr/include/c++/11/bits/align.h \
244
+ /usr/include/c++/11/bit \
245
+ /usr/include/c++/11/bits/unique_ptr.h \
246
+ /usr/include/c++/11/bits/shared_ptr.h \
247
+ /usr/include/c++/11/iosfwd \
248
+ /usr/include/c++/11/bits/stringfwd.h \
249
+ /usr/include/c++/11/bits/postypes.h \
250
+ /usr/include/c++/11/cwchar \
251
+ /usr/include/wchar.h \
252
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
255
+ /usr/include/c++/11/bits/shared_ptr_base.h \
256
+ /usr/include/c++/11/bits/allocated_ptr.h \
257
+ /usr/include/c++/11/ext/atomicity.h \
258
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
260
+ /usr/include/pthread.h \
261
+ /usr/include/sched.h \
262
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
264
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
265
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
266
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
267
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
268
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
269
+ /usr/include/c++/11/ext/concurrence.h \
270
+ /usr/include/c++/11/exception \
271
+ /usr/include/c++/11/bits/exception_ptr.h \
272
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
273
+ /usr/include/c++/11/bits/nested_exception.h \
274
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
275
+ /usr/include/c++/11/bits/atomic_base.h \
276
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
277
+ /usr/include/c++/11/backward/auto_ptr.h \
278
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
279
+ /usr/include/c++/11/pstl/execution_defs.h \
280
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
281
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
285
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
286
+ /usr/include/c++/11/cassert \
287
+ /usr/include/c++/11/cfloat \
288
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
289
+ /usr/include/c++/11/cstdio \
290
+ /usr/include/c++/11/string \
291
+ /usr/include/c++/11/bits/char_traits.h \
292
+ /usr/include/c++/11/bits/localefwd.h \
293
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
294
+ /usr/include/c++/11/clocale \
295
+ /usr/include/locale.h \
296
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
297
+ /usr/include/c++/11/cctype \
298
+ /usr/include/c++/11/bits/ostream_insert.h \
299
+ /usr/include/c++/11/bits/cxxabi_forced.h \
300
+ /usr/include/c++/11/bits/basic_string.h \
301
+ /usr/include/c++/11/string_view \
302
+ /usr/include/c++/11/bits/string_view.tcc \
303
+ /usr/include/c++/11/ext/string_conversions.h \
304
+ /usr/include/c++/11/cerrno \
305
+ /usr/include/errno.h \
306
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
307
+ /usr/include/linux/errno.h \
308
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
309
+ /usr/include/asm-generic/errno.h \
310
+ /usr/include/asm-generic/errno-base.h \
311
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
312
+ /usr/include/c++/11/bits/charconv.h \
313
+ /usr/include/c++/11/bits/basic_string.tcc \
314
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
315
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
323
+ /content/tmp/ggml/src/ggml-cuda/fattn-common.cuh \
324
+ /content/tmp/ggml/src/ggml-cuda/convert.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/vecdotq.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/fattn-wmma-f16.cuh \
327
+ /usr/local/cuda/targets/x86_64-linux/include/mma.h \
328
+ /usr/local/cuda/targets/x86_64-linux/include/crt/mma.h \
329
+ /usr/local/cuda/targets/x86_64-linux/include/crt/mma.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o.d ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o : /content/tmp/ggml/src/ggml-cuda/getrows.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/getrows.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/dequantize.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/convert.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gla.cu.o ADDED
Binary file (91.9 kB). View file
 
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp ADDED
@@ -0,0 +1 @@
 
 
1
+ -I"/content/tmp/ggml/src/ggml-cuda/.." -I/content/tmp/ggml/src/../include -isystem "/usr/local/cuda/targets/x86_64-linux/include"
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/link.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ /usr/bin/g++ -fPIC -shared -Wl,-soname,libggml-cuda.so -o ../../../bin/libggml-cuda.so @CMakeFiles/ggml-cuda.dir/objects1.rsp @CMakeFiles/ggml-cuda.dir/linkLibs.rsp -L"/usr/local/cuda/targets/x86_64-linux/lib/stubs" -L"/usr/local/cuda/targets/x86_64-linux/lib"
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o.d ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o : /content/tmp/ggml/src/ggml-cuda/mmf.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/../include/ggml.h \
229
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
230
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
231
+ /usr/include/stdint.h \
232
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
233
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
234
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
235
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
236
+ /content/tmp/ggml/src/../include/gguf.h \
237
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
238
+ /content/tmp/ggml/src/../include/ggml-backend.h \
239
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
240
+ /usr/include/c++/11/cstdint \
241
+ /usr/include/c++/11/memory \
242
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
243
+ /usr/include/c++/11/bits/align.h \
244
+ /usr/include/c++/11/bit \
245
+ /usr/include/c++/11/bits/unique_ptr.h \
246
+ /usr/include/c++/11/bits/shared_ptr.h \
247
+ /usr/include/c++/11/iosfwd \
248
+ /usr/include/c++/11/bits/stringfwd.h \
249
+ /usr/include/c++/11/bits/postypes.h \
250
+ /usr/include/c++/11/cwchar \
251
+ /usr/include/wchar.h \
252
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
255
+ /usr/include/c++/11/bits/shared_ptr_base.h \
256
+ /usr/include/c++/11/bits/allocated_ptr.h \
257
+ /usr/include/c++/11/ext/atomicity.h \
258
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
260
+ /usr/include/pthread.h \
261
+ /usr/include/sched.h \
262
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
264
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
265
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
266
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
267
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
268
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
269
+ /usr/include/c++/11/ext/concurrence.h \
270
+ /usr/include/c++/11/exception \
271
+ /usr/include/c++/11/bits/exception_ptr.h \
272
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
273
+ /usr/include/c++/11/bits/nested_exception.h \
274
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
275
+ /usr/include/c++/11/bits/atomic_base.h \
276
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
277
+ /usr/include/c++/11/backward/auto_ptr.h \
278
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
279
+ /usr/include/c++/11/pstl/execution_defs.h \
280
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
281
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
285
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
286
+ /usr/include/c++/11/cassert \
287
+ /usr/include/c++/11/cfloat \
288
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
289
+ /usr/include/c++/11/cstdio \
290
+ /usr/include/c++/11/string \
291
+ /usr/include/c++/11/bits/char_traits.h \
292
+ /usr/include/c++/11/bits/localefwd.h \
293
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
294
+ /usr/include/c++/11/clocale \
295
+ /usr/include/locale.h \
296
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
297
+ /usr/include/c++/11/cctype \
298
+ /usr/include/c++/11/bits/ostream_insert.h \
299
+ /usr/include/c++/11/bits/cxxabi_forced.h \
300
+ /usr/include/c++/11/bits/basic_string.h \
301
+ /usr/include/c++/11/string_view \
302
+ /usr/include/c++/11/bits/string_view.tcc \
303
+ /usr/include/c++/11/ext/string_conversions.h \
304
+ /usr/include/c++/11/cerrno \
305
+ /usr/include/errno.h \
306
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
307
+ /usr/include/linux/errno.h \
308
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
309
+ /usr/include/asm-generic/errno.h \
310
+ /usr/include/asm-generic/errno-base.h \
311
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
312
+ /usr/include/c++/11/bits/charconv.h \
313
+ /usr/include/c++/11/bits/basic_string.tcc \
314
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
315
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
323
+ /content/tmp/ggml/src/ggml-cuda/mma.cuh \
324
+ /content/tmp/ggml/src/ggml-cuda/mmf.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o.d ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o : /content/tmp/ggml/src/ggml-cuda/mmq.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/mmq.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/vecdotq.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/mma.cuh \
326
+ /usr/include/c++/11/climits \
327
+ /content/tmp/ggml/src/ggml-cuda/quantize.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o : /content/tmp/ggml/src/ggml-cuda/opt-step-sgd.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
229
+ /content/tmp/ggml/src/../include/ggml.h \
230
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
232
+ /usr/include/stdint.h \
233
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
234
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
235
+ /content/tmp/ggml/src/../include/gguf.h \
236
+ /content/tmp/ggml/src/ggml-cuda/opt-step-sgd.cuh \
237
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o : /content/tmp/ggml/src/ggml-cuda/out-prod.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/out-prod.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o : /content/tmp/ggml/src/ggml-cuda/pad.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/pad.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/progress.make ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ CMAKE_PROGRESS_1 = 20
2
+ CMAKE_PROGRESS_2 =
3
+ CMAKE_PROGRESS_3 = 21
4
+ CMAKE_PROGRESS_4 =
5
+ CMAKE_PROGRESS_5 = 22
6
+ CMAKE_PROGRESS_6 =
7
+ CMAKE_PROGRESS_7 = 23
8
+ CMAKE_PROGRESS_8 =
9
+ CMAKE_PROGRESS_9 = 24
10
+ CMAKE_PROGRESS_10 =
11
+ CMAKE_PROGRESS_11 = 25
12
+ CMAKE_PROGRESS_12 =
13
+ CMAKE_PROGRESS_13 =
14
+ CMAKE_PROGRESS_14 = 26
15
+ CMAKE_PROGRESS_15 =
16
+ CMAKE_PROGRESS_16 = 27
17
+ CMAKE_PROGRESS_17 =
18
+ CMAKE_PROGRESS_18 = 28
19
+ CMAKE_PROGRESS_19 =
20
+ CMAKE_PROGRESS_20 = 29
21
+ CMAKE_PROGRESS_21 =
22
+ CMAKE_PROGRESS_22 = 30
23
+ CMAKE_PROGRESS_23 =
24
+ CMAKE_PROGRESS_24 = 31
25
+ CMAKE_PROGRESS_25 =
26
+ CMAKE_PROGRESS_26 = 32
27
+ CMAKE_PROGRESS_27 =
28
+ CMAKE_PROGRESS_28 = 33
29
+ CMAKE_PROGRESS_29 =
30
+ CMAKE_PROGRESS_30 =
31
+ CMAKE_PROGRESS_31 = 34
32
+ CMAKE_PROGRESS_32 =
33
+ CMAKE_PROGRESS_33 = 35
34
+ CMAKE_PROGRESS_34 =
35
+ CMAKE_PROGRESS_35 = 36
36
+ CMAKE_PROGRESS_36 =
37
+ CMAKE_PROGRESS_37 = 37
38
+ CMAKE_PROGRESS_38 =
39
+ CMAKE_PROGRESS_39 = 38
40
+ CMAKE_PROGRESS_40 =
41
+ CMAKE_PROGRESS_41 = 39
42
+ CMAKE_PROGRESS_42 =
43
+ CMAKE_PROGRESS_43 = 40
44
+ CMAKE_PROGRESS_44 =
45
+ CMAKE_PROGRESS_45 = 41
46
+ CMAKE_PROGRESS_46 =
47
+ CMAKE_PROGRESS_47 =
48
+ CMAKE_PROGRESS_48 = 42
49
+ CMAKE_PROGRESS_49 =
50
+ CMAKE_PROGRESS_50 = 43
51
+ CMAKE_PROGRESS_51 =
52
+ CMAKE_PROGRESS_52 = 44
53
+ CMAKE_PROGRESS_53 =
54
+ CMAKE_PROGRESS_54 = 45
55
+ CMAKE_PROGRESS_55 =
56
+ CMAKE_PROGRESS_56 = 46
57
+ CMAKE_PROGRESS_57 =
58
+ CMAKE_PROGRESS_58 = 47
59
+ CMAKE_PROGRESS_59 =
60
+ CMAKE_PROGRESS_60 = 48
61
+ CMAKE_PROGRESS_61 =
62
+ CMAKE_PROGRESS_62 = 49
63
+ CMAKE_PROGRESS_63 =
64
+ CMAKE_PROGRESS_64 = 50
65
+ CMAKE_PROGRESS_65 =
66
+ CMAKE_PROGRESS_66 =
67
+ CMAKE_PROGRESS_67 = 51
68
+ CMAKE_PROGRESS_68 =
69
+ CMAKE_PROGRESS_69 = 52
70
+ CMAKE_PROGRESS_70 =
71
+ CMAKE_PROGRESS_71 = 53
72
+ CMAKE_PROGRESS_72 =
73
+ CMAKE_PROGRESS_73 = 54
74
+ CMAKE_PROGRESS_74 =
75
+ CMAKE_PROGRESS_75 = 55
76
+ CMAKE_PROGRESS_76 =
77
+ CMAKE_PROGRESS_77 = 56
78
+ CMAKE_PROGRESS_78 =
79
+ CMAKE_PROGRESS_79 = 57
80
+ CMAKE_PROGRESS_80 =
81
+ CMAKE_PROGRESS_81 = 58
82
+ CMAKE_PROGRESS_82 =
83
+ CMAKE_PROGRESS_83 =
84
+ CMAKE_PROGRESS_84 = 59
85
+ CMAKE_PROGRESS_85 =
86
+ CMAKE_PROGRESS_86 = 60
87
+ CMAKE_PROGRESS_87 =
88
+ CMAKE_PROGRESS_88 = 61
89
+ CMAKE_PROGRESS_89 =
90
+ CMAKE_PROGRESS_90 = 62
91
+ CMAKE_PROGRESS_91 =
92
+ CMAKE_PROGRESS_92 = 63
93
+ CMAKE_PROGRESS_93 =
94
+ CMAKE_PROGRESS_94 = 64
95
+ CMAKE_PROGRESS_95 =
96
+ CMAKE_PROGRESS_96 = 65
97
+ CMAKE_PROGRESS_97 =
98
+ CMAKE_PROGRESS_98 = 66
99
+ CMAKE_PROGRESS_99 =
100
+
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o.d ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o : /content/tmp/ggml/src/ggml-cuda/set-rows.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/set-rows.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/cpy-utils.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/convert.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o.d ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o : /content/tmp/ggml/src/ggml-cuda/softcap.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/softcap.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o.d ADDED
@@ -0,0 +1,1038 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o : /content/tmp/ggml/src/ggml-cuda/ssm-scan.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /usr/local/cuda/targets/x86_64-linux/include/cub/cub.cuh \
229
+ /usr/local/cuda/targets/x86_64-linux/include/cub/config.cuh \
230
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/__cccl_config \
231
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl_config \
232
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/compiler.h \
233
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/diagnostic.h \
234
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/compiler.h \
235
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/system_header.h \
236
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/dialect.h \
237
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/execution_space.h \
238
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/ptx_isa.h \
239
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
240
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
241
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
242
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/system_header.h \
243
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/version.h \
244
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cccl/visibility.h \
245
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_arch.cuh \
246
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_cpp_dialect.cuh \
247
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_compiler.cuh \
248
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_macro.cuh \
249
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/detect_cuda_runtime.cuh \
250
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_namespace.cuh \
251
+ /usr/local/cuda/targets/x86_64-linux/include/cub/version.cuh \
252
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/version \
253
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/version \
254
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/__config \
255
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__config \
256
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/__pragma_push \
257
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__pragma_push \
258
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__undef_macros \
259
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/version \
260
+ /usr/include/c++/11/version \
261
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/__pragma_pop \
262
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__pragma_pop \
263
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/utility \
264
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/utility \
265
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__assert \
266
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__verbose_abort \
267
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__availability \
268
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__debug \
269
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_constant_evaluated.h \
270
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/cstddef \
271
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/cstddef_prelude.h \
272
+ /usr/include/c++/11/cstddef \
273
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/enable_if.h \
274
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_integral.h \
275
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/integral_constant.h \
276
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_cv.h \
277
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_const.h \
278
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_volatile.h \
279
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/binary_function.h \
280
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/hash.h \
281
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/invoke.h \
282
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/add_lvalue_reference.h \
283
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_referenceable.h \
284
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_same.h \
285
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/apply_cv.h \
286
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_const.h \
287
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_volatile.h \
288
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_reference.h \
289
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/cstddef \
290
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/conditional.h \
291
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/decay.h \
292
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/add_pointer.h \
293
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_void.h \
294
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_cvref.h \
295
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_array.h \
296
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_function.h \
297
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_reference.h \
298
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_extent.h \
299
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/enable_if.h \
300
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_base_of.h \
301
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_class.h \
302
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_union.h \
303
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/declval.h \
304
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_core_convertible.h \
305
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_member_function_pointer.h \
306
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_member_object_pointer.h \
307
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_reference_wrapper.h \
308
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/nat.h \
309
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/forward.h \
310
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/unary_function.h \
311
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/hash.h \
312
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_enum.h \
313
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_floating_point.h \
314
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_integral.h \
315
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_member_pointer.h \
316
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_pointer.h \
317
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_copy_constructible.h \
318
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/add_const.h \
319
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_constructible.h \
320
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/conjunction.h \
321
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/disjunction.h \
322
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_destructible.h \
323
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_all_extents.h \
324
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/negation.h \
325
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_default_constructible.h \
326
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_move_constructible.h \
327
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/add_rvalue_reference.h \
328
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/underlying_type.h \
329
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/move.h \
330
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_move_constructible.h \
331
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_constructible.h \
332
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_scalar.h \
333
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_arithmetic.h \
334
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_null_pointer.h \
335
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/pair.h \
336
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/unwrap_ref.h \
337
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/get.h \
338
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/copyable.h \
339
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/__concept_macros.h \
340
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/assignable.h \
341
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/common_reference_with.h \
342
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/convertible_to.h \
343
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_convertible.h \
344
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/same_as.h \
345
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/common_reference.h \
346
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/common_type.h \
347
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/void_t.h \
348
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/copy_cv.h \
349
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/add_cv.h \
350
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/add_volatile.h \
351
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/copy_cvref.h \
352
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/make_const_lvalue_ref.h \
353
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/constructible.h \
354
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/destructible.h \
355
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_object.h \
356
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_destructible.h \
357
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/movable.h \
358
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/swappable.h \
359
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/class_or_enum.h \
360
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/extent.h \
361
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_move_assignable.h \
362
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_assignable.h \
363
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_assignable.h \
364
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/type_identity.h \
365
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/exchange.h \
366
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/array.h \
367
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/pair.h \
368
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/subrange.h \
369
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/concepts.h \
370
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/arithmetic.h \
371
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_signed.h \
372
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_signed_integer.h \
373
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_unsigned_integer.h \
374
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/derived_from.h \
375
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/equality_comparable.h \
376
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/boolean_testable.h \
377
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/invocable.h \
378
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/predicate.h \
379
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/regular.h \
380
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/semiregular.h \
381
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/relation.h \
382
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/totally_ordered.h \
383
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/incrementable_traits.h \
384
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_primary_template.h \
385
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_valid_expansion.h \
386
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/make_signed.h \
387
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/type_list.h \
388
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iter_move.h \
389
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iterator_traits.h \
390
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/readable_traits.h \
391
+ /usr/include/c++/11/iterator \
392
+ /usr/include/c++/11/iosfwd \
393
+ /usr/include/c++/11/bits/stringfwd.h \
394
+ /usr/include/c++/11/bits/postypes.h \
395
+ /usr/include/c++/11/cwchar \
396
+ /usr/include/wchar.h \
397
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
398
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
399
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
400
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
401
+ /usr/include/c++/11/bits/stream_iterator.h \
402
+ /usr/include/c++/11/bits/streambuf_iterator.h \
403
+ /usr/include/c++/11/streambuf \
404
+ /usr/include/c++/11/bits/localefwd.h \
405
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
406
+ /usr/include/c++/11/clocale \
407
+ /usr/include/locale.h \
408
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
409
+ /usr/include/c++/11/cctype \
410
+ /usr/include/c++/11/bits/ios_base.h \
411
+ /usr/include/c++/11/ext/atomicity.h \
412
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
413
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
414
+ /usr/include/pthread.h \
415
+ /usr/include/sched.h \
416
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
417
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
418
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
419
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
420
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
421
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
422
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
423
+ /usr/include/c++/11/bits/locale_classes.h \
424
+ /usr/include/c++/11/string \
425
+ /usr/include/c++/11/bits/char_traits.h \
426
+ /usr/include/c++/11/cstdint \
427
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
428
+ /usr/include/stdint.h \
429
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
430
+ /usr/include/c++/11/bits/ostream_insert.h \
431
+ /usr/include/c++/11/bits/cxxabi_forced.h \
432
+ /usr/include/c++/11/bits/basic_string.h \
433
+ /usr/include/c++/11/string_view \
434
+ /usr/include/c++/11/bits/string_view.tcc \
435
+ /usr/include/c++/11/ext/string_conversions.h \
436
+ /usr/include/c++/11/cstdio \
437
+ /usr/include/c++/11/cerrno \
438
+ /usr/include/errno.h \
439
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
440
+ /usr/include/linux/errno.h \
441
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
442
+ /usr/include/asm-generic/errno.h \
443
+ /usr/include/asm-generic/errno-base.h \
444
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
445
+ /usr/include/c++/11/bits/charconv.h \
446
+ /usr/include/c++/11/bits/basic_string.tcc \
447
+ /usr/include/c++/11/bits/locale_classes.tcc \
448
+ /usr/include/c++/11/system_error \
449
+ /usr/include/x86_64-linux-gnu/c++/11/bits/error_constants.h \
450
+ /usr/include/c++/11/stdexcept \
451
+ /usr/include/c++/11/exception \
452
+ /usr/include/c++/11/bits/exception_ptr.h \
453
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
454
+ /usr/include/c++/11/bits/nested_exception.h \
455
+ /usr/include/c++/11/bits/streambuf.tcc \
456
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/pointer_traits.h \
457
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/addressof.h \
458
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/tuple.h \
459
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_element.h \
460
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_indices.h \
461
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/integer_sequence.h \
462
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_types.h \
463
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/sfinae_helpers.h \
464
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/make_tuple_types.h \
465
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/apply_cv.h \
466
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_size.h \
467
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_like_ext.h \
468
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/structured_bindings.h \
469
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_copy_assignable.h \
470
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_implicitly_default_constructible.h \
471
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_move_assignable.h \
472
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_copy_assignable.h \
473
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_copy_constructible.h \
474
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_default_constructible.h \
475
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_swappable.h \
476
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/piecewise_construct.h \
477
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/swap.h \
478
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/cstdint \
479
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/cstdint_prelude.h \
480
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/climits \
481
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/climits_prelude.h \
482
+ /usr/include/c++/11/climits \
483
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/version \
484
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/reference_wrapper.h \
485
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/weak_result_type.h \
486
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/binary_function.h \
487
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/unary_function.h \
488
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/unwrap_ref.h \
489
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/weak_result_type.h \
490
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/get.h \
491
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/sfinae_helpers.h \
492
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/structured_bindings.h \
493
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/as_const.h \
494
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/auto_cast.h \
495
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/cmp.h \
496
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/make_unsigned.h \
497
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_unsigned.h \
498
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/limits \
499
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__assert \
500
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/type_traits \
501
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__algorithm/iter_swap.h \
502
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/identity.h \
503
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/reference_wrapper.h \
504
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/aligned_storage.h \
505
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/aligned_union.h \
506
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/alignment_of.h \
507
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/can_extract_key.h \
508
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_const_ref.h \
509
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/dependent_type.h \
510
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/has_unique_object_representation.h \
511
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/has_virtual_destructor.h \
512
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_abstract.h \
513
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_aggregate.h \
514
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_allocator.h \
515
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_bounded_array.h \
516
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_callable.h \
517
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_char_like_type.h \
518
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_standard_layout.h \
519
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivial.h \
520
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_copyable.h \
521
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_default_constructible.h \
522
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_constructible.h \
523
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_compound.h \
524
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_fundamental.h \
525
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_constant_evaluated.h \
526
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_empty.h \
527
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_final.h \
528
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_literal_type.h \
529
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_nothrow_convertible.h \
530
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/lazy.h \
531
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_pod.h \
532
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_copy_constructible.h \
533
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_copy_assignable.h \
534
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_assignable.h \
535
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_destructible.h \
536
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_polymorphic.h \
537
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_scoped_enum.h \
538
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_move_assignable.h \
539
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_trivially_move_constructible.h \
540
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_unbounded_array.h \
541
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/make_32_64_or_128_bit.h \
542
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/maybe_const.h \
543
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/promote.h \
544
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
545
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
546
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
547
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
548
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/rank.h \
549
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_pointer.h \
550
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/result_of.h \
551
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/convert_to_integral.h \
552
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/convert_to_integral.h \
553
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/declval.h \
554
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/exchange.h \
555
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/forward_like.h \
556
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/forward.h \
557
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/in_place.h \
558
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/integer_sequence.h \
559
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/move.h \
560
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/pair.h \
561
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/piecewise_construct.h \
562
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/priority_tag.h \
563
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/rel_ops.h \
564
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/swap.h \
565
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/to_underlying.h \
566
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/unreachable.h \
567
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/cstdlib \
568
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/construct_at.h \
569
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/access.h \
570
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/voidify.h \
571
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/voidify.h \
572
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/limits \
573
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/type_traits \
574
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/concepts \
575
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/__concept_macros.h \
576
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/_One_of.h \
577
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/arithmetic.h \
578
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/assignable.h \
579
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/boolean_testable.h \
580
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/class_or_enum.h \
581
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/common_reference_with.h \
582
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/common_with.h \
583
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/constructible.h \
584
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/convertible_to.h \
585
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/copyable.h \
586
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/derived_from.h \
587
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/destructible.h \
588
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/different_from.h \
589
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/equality_comparable.h \
590
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/invocable.h \
591
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/movable.h \
592
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/predicate.h \
593
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/regular.h \
594
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/relation.h \
595
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/same_as.h \
596
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/semiregular.h \
597
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/swappable.h \
598
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__concepts/totally_ordered.h \
599
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/initializer_list \
600
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_element.h \
601
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_size.h \
602
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_deprecated.cuh \
603
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/type_traits.cuh \
604
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/functional \
605
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/functional \
606
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional_base \
607
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/operations.h \
608
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/integral_constant.h \
609
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_constructible.h \
610
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_convertible.h \
611
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/remove_cvref.h \
612
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/binary_negate.h \
613
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/bind_back.h \
614
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/perfect_forward.h \
615
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/tuple \
616
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional_base \
617
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__tuple_dir/tuple_like.h \
618
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/utility \
619
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/bind_front.h \
620
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/bind.h \
621
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/binder1st.h \
622
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/binder2nd.h \
623
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/compose.h \
624
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/default_searcher.h \
625
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__algorithm/search.h \
626
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__algorithm/comp.h \
627
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/advance.h \
628
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/operations.h \
629
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/function.h \
630
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__debug \
631
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/identity.h \
632
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/invoke.h \
633
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/is_transparent.h \
634
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/mem_fn.h \
635
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/mem_fun_ref.h \
636
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/not_fn.h \
637
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/perfect_forward.h \
638
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/pointer_to_binary_function.h \
639
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/pointer_to_unary_function.h \
640
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/ranges_operations.h \
641
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/unary_negate.h \
642
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/iosfwd \
643
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/string.h \
644
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__fwd/memory_resource.h \
645
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/type_traits \
646
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_debug.cuh \
647
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_adjacent_difference.cuh \
648
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_ptx.cuh \
649
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/cpp_compatibility.cuh \
650
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_type.cuh \
651
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/limits \
652
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
653
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
654
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/uninitialized_copy.cuh \
655
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/cstdint \
656
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/cstdint \
657
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_discontinuity.cuh \
658
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_exchange.cuh \
659
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/warp_exchange.cuh \
660
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/specializations/warp_exchange_shfl.cuh \
661
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/specializations/warp_exchange_smem.cuh \
662
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_histogram.cuh \
663
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_histogram_atomic.cuh \
664
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_histogram_sort.cuh \
665
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_radix_sort.cuh \
666
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_radix_rank.cuh \
667
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_scan.cuh \
668
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_scan_raking.cuh \
669
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_raking_layout.cuh \
670
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_reduce.cuh \
671
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_operators.cuh \
672
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_scan.cuh \
673
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/warp_scan.cuh \
674
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/specializations/warp_scan_shfl.cuh \
675
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/specializations/warp_scan_smem.cuh \
676
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_load.cuh \
677
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_store.cuh \
678
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_scan_warp_scans.cuh \
679
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/radix_rank_sort_operations.cuh \
680
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/type_traits/integer_sequence.h \
681
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config.h \
682
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/version.h \
683
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/config.h \
684
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/simple_defines.h \
685
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/compiler.h \
686
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/cpp_dialect.h \
687
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/cpp_compatibility.h \
688
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/cstddef \
689
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/deprecated.h \
690
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/host_system.h \
691
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/device_system.h \
692
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/debug.h \
693
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/global_workarounds.h \
694
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/config/namespace.h \
695
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/cpp11_required.h \
696
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/tuple \
697
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/tuple \
698
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_load.cuh \
699
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/cache_modified_input_iterator.cuh \
700
+ /usr/include/c++/11/iostream \
701
+ /usr/include/c++/11/ostream \
702
+ /usr/include/c++/11/ios \
703
+ /usr/include/c++/11/bits/basic_ios.h \
704
+ /usr/include/c++/11/bits/locale_facets.h \
705
+ /usr/include/c++/11/cwctype \
706
+ /usr/include/wctype.h \
707
+ /usr/include/x86_64-linux-gnu/bits/wctype-wchar.h \
708
+ /usr/include/x86_64-linux-gnu/c++/11/bits/ctype_base.h \
709
+ /usr/include/x86_64-linux-gnu/c++/11/bits/ctype_inline.h \
710
+ /usr/include/c++/11/bits/locale_facets.tcc \
711
+ /usr/include/c++/11/bits/basic_ios.tcc \
712
+ /usr/include/c++/11/bits/ostream.tcc \
713
+ /usr/include/c++/11/istream \
714
+ /usr/include/c++/11/bits/istream.tcc \
715
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/iterator_facade.h \
716
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits.h \
717
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits/has_trivial_assign.h \
718
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_facade_category.h \
719
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/host_system_tag.h \
720
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cpp/detail/execution_policy.h \
721
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/sequential/execution_policy.h \
722
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/execution_policy.h \
723
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/device_system_tag.h \
724
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/detail/execution_policy.h \
725
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/any_system_tag.h \
726
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/config.h \
727
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/allocator_aware_execution_policy.h \
728
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/execute_with_allocator_fwd.h \
729
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/execute_with_dependencies.h \
730
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_deduction.h \
731
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/preprocessor.h \
732
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/type_traits/remove_cvref.h \
733
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/alignment.h \
734
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/dependencies_aware_execution_policy.h \
735
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/iterator_categories.h \
736
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_category_with_system_and_traversal.h \
737
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_traversal_tags.h \
738
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/universal_categories.h \
739
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/is_iterator_category.h \
740
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_category_to_traversal.h \
741
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_category_to_system.h \
742
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/distance_from_result.h \
743
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/iterator_traits.h \
744
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/type_traits/void_t.h \
745
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_traits.inl \
746
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_merge_sort.cuh \
747
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_sort.cuh \
748
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_math.cuh \
749
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_reduce.cuh \
750
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_reduce_raking.cuh \
751
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/warp_reduce.cuh \
752
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/specializations/warp_reduce_shfl.cuh \
753
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/specializations/warp_reduce_smem.cuh \
754
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_reduce_raking_commutative_only.cuh \
755
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/specializations/block_reduce_warp_reductions.cuh \
756
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_store.cuh \
757
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_adjacent_difference.cuh \
758
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/choose_offset.cuh \
759
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/iterator \
760
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/iterator \
761
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/access.h \
762
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/advance.h \
763
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/back_insert_iterator.h \
764
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iterator.h \
765
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/bounded_iter.h \
766
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/concepts.h \
767
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/data.h \
768
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/initializer_list \
769
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/default_sentinel.h \
770
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/distance.h \
771
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__ranges/access.h \
772
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__ranges/enable_borrowed_range.h \
773
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__utility/auto_cast.h \
774
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__ranges/concepts.h \
775
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__ranges/data.h \
776
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/reverse_iterator.h \
777
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__algorithm/unwrap_iter.h \
778
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iter_swap.h \
779
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/next.h \
780
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/prev.h \
781
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__ranges/enable_view.h \
782
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__ranges/size.h \
783
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/empty.h \
784
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/erase_if_container.h \
785
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/front_insert_iterator.h \
786
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/incrementable_traits.h \
787
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/indirectly_comparable.h \
788
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/projected.h \
789
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/insert_iterator.h \
790
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/istream_iterator.h \
791
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/default_sentinel.h \
792
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/iosfwd \
793
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/istreambuf_iterator.h \
794
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iter_move.h \
795
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iter_swap.h \
796
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iterator.h \
797
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/iterator_traits.h \
798
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/mergeable.h \
799
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__functional/ranges_operations.h \
800
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/move_iterator.h \
801
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/move_sentinel.h \
802
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/move_sentinel.h \
803
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/next.h \
804
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/ostream_iterator.h \
805
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/ostreambuf_iterator.h \
806
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/permutable.h \
807
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/prev.h \
808
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/projected.h \
809
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/readable_traits.h \
810
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/reverse_access.h \
811
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/reverse_iterator.h \
812
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/size.h \
813
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/sortable.h \
814
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/permutable.h \
815
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/unreachable_sentinel.h \
816
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__iterator/wrap_iter.h \
817
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/addressof.h \
818
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__memory/pointer_traits.h \
819
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__type_traits/is_pointer.h \
820
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_adjacent_difference.cuh \
821
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_adjacent_difference.cuh \
822
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/detail/core/util.h \
823
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/raw_pointer_cast.h \
824
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits/pointer_traits.h \
825
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits/is_metafunction_defined.h \
826
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits/has_nested_type.h \
827
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/detail/util.h \
828
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system_error.h \
829
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/error_code.h \
830
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/errno.h \
831
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/error_category.inl \
832
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/functional.h \
833
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/placeholder.h \
834
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/actor.h \
835
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/tuple.h \
836
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/value.h \
837
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/composite.h \
838
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/assignment_operator.h \
839
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/operator_adaptors.h \
840
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/argument.h \
841
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/raw_reference_cast.h \
842
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/tuple_transform.h \
843
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/tuple_meta_transform.h \
844
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits/result_of_adaptable_function.h \
845
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/type_traits/function_traits.h \
846
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/actor.inl \
847
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/type_traits/logical_metafunctions.h \
848
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional.inl \
849
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators.h \
850
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/arithmetic_operators.h \
851
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/relational_operators.h \
852
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/logical_operators.h \
853
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/bitwise_operators.h \
854
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/functional/operators/compound_assignment_operators.h \
855
+ /usr/include/c++/11/cstring \
856
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/error_code.inl \
857
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/error_condition.inl \
858
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/system_error.h \
859
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/system_error.inl \
860
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/error.h \
861
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/detail/error.inl \
862
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/device_synchronize.cuh \
863
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_device.cuh \
864
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_temporary_storage.cuh \
865
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/discard_memory \
866
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/ptx \
867
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx.h \
868
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/barrier_cluster.h \
869
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/ptx_dot_variants.h \
870
+ /usr/local/cuda-12.5/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/ptx_helper_functions.h \
871
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/cp_async_bulk.h \
872
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/cp_async_bulk_commit_group.h \
873
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/cp_async_bulk_tensor.h \
874
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/cp_async_bulk_wait_group.h \
875
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/cp_reduce_async_bulk.h \
876
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/cp_reduce_async_bulk_tensor.h \
877
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/fence.h \
878
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/get_sreg.h \
879
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/getctarank.h \
880
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/mbarrier_arrive.h \
881
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/mbarrier_init.h \
882
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/mbarrier_wait.h \
883
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/red_async.h \
884
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/st_async.h \
885
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/tensormap_cp_fenceproxy.h \
886
+ /usr/local/cuda/targets/x86_64-linux/include/cuda/std/detail/libcxx/include/__cuda/ptx/instructions/tensormap_replace.h \
887
+ /usr/include/c++/11/atomic \
888
+ /usr/include/c++/11/bits/atomic_base.h \
889
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
890
+ /usr/include/c++/11/cassert \
891
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/type_traits/is_contiguous_iterator.h \
892
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/detail/core/triple_chevron_launch.h \
893
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/cuda/detail/core/alignment.h \
894
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/integer_traits.h \
895
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/cstdint.h \
896
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_copy.cuh \
897
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_batch_memcpy.cuh \
898
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_batch_memcpy.cuh \
899
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/single_pass_scan_operators.cuh \
900
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/strong_load.cuh \
901
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/strong_store.cuh \
902
+ /usr/local/cuda/targets/x86_64-linux/include/cub/block/block_run_length_decode.cuh \
903
+ /usr/local/cuda/targets/x86_64-linux/include/cub/thread/thread_search.cuh \
904
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/temporary_storage.cuh \
905
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_histogram.cuh \
906
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_histogram.cuh \
907
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_histogram.cuh \
908
+ /usr/local/cuda/targets/x86_64-linux/include/cub/grid/grid_queue.cuh \
909
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_histogram.cuh \
910
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_memcpy.cuh \
911
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_merge_sort.cuh \
912
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_merge_sort.cuh \
913
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_merge_sort.cuh \
914
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/integer_math.h \
915
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_partition.cuh \
916
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_select_if.cuh \
917
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_select_if.cuh \
918
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_scan.cuh \
919
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_scan.cuh \
920
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_scan.cuh \
921
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_select_if.cuh \
922
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_three_way_partition.cuh \
923
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_three_way_partition.cuh \
924
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_three_way_partition.cuh \
925
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_radix_sort.cuh \
926
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_radix_sort.cuh \
927
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_radix_sort_downsweep.cuh \
928
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_radix_sort_histogram.cuh \
929
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_radix_sort_onesweep.cuh \
930
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_radix_sort_upsweep.cuh \
931
+ /usr/local/cuda/targets/x86_64-linux/include/cub/grid/grid_even_share.cuh \
932
+ /usr/local/cuda/targets/x86_64-linux/include/cub/grid/grid_mapping.cuh \
933
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_reduce.cuh \
934
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_reduce.cuh \
935
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_reduce.cuh \
936
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/arg_index_input_iterator.cuh \
937
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_reduce_by_key.cuh \
938
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_reduce_by_key.cuh \
939
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/constant_input_iterator.cuh \
940
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_reduce_by_key.cuh \
941
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_run_length_encode.cuh \
942
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_rle.cuh \
943
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_rle.cuh \
944
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_run_length_encode.cuh \
945
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_scan.cuh \
946
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_scan_by_key.cuh \
947
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_scan_by_key.cuh \
948
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_scan_by_key.cuh \
949
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_segmented_radix_sort.cuh \
950
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_segmented_reduce.cuh \
951
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_segmented_sort.cuh \
952
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_segmented_sort.cuh \
953
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_segmented_radix_sort.cuh \
954
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_sub_warp_merge_sort.cuh \
955
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/warp_load.cuh \
956
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/warp_merge_sort.cuh \
957
+ /usr/local/cuda/targets/x86_64-linux/include/cub/warp/warp_store.cuh \
958
+ /usr/local/cuda/targets/x86_64-linux/include/cub/detail/device_double_buffer.cuh \
959
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/counting_iterator.h \
960
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/iterator_adaptor.h \
961
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/use_default.h \
962
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/iterator_adaptor_base.h \
963
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/counting_iterator.inl \
964
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/numeric_traits.h \
965
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/reverse_iterator.h \
966
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/reverse_iterator_base.h \
967
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/iterator/detail/reverse_iterator.inl \
968
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_select.cuh \
969
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_unique_by_key.cuh \
970
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_unique_by_key.cuh \
971
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_unique_by_key.cuh \
972
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_spmv.cuh \
973
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_spmv_orig.cuh \
974
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_segment_fixup.cuh \
975
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_spmv_orig.cuh \
976
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/counting_input_iterator.cuh \
977
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/device_for.cuh \
978
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/dispatch_for.cuh \
979
+ /usr/local/cuda/targets/x86_64-linux/include/cub/agent/agent_for.cuh \
980
+ /usr/local/cuda/targets/x86_64-linux/include/cub/device/dispatch/tuning/tuning_for.cuh \
981
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/distance.h \
982
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/distance.inl \
983
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/advance.h \
984
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/detail/advance.inl \
985
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/generic/advance.h \
986
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/generic/advance.inl \
987
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/generic/distance.h \
988
+ /usr/local/cuda/targets/x86_64-linux/include/thrust/system/detail/generic/distance.inl \
989
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/cache_modified_output_iterator.cuh \
990
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/discard_output_iterator.cuh \
991
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/tex_obj_input_iterator.cuh \
992
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/tex_ref_input_iterator.cuh \
993
+ /usr/local/cuda/targets/x86_64-linux/include/cub/iterator/transform_input_iterator.cuh \
994
+ /usr/local/cuda/targets/x86_64-linux/include/cub/util_allocator.cuh \
995
+ /usr/include/c++/11/map \
996
+ /usr/include/c++/11/bits/stl_tree.h \
997
+ /usr/include/c++/11/bits/stl_map.h \
998
+ /usr/include/c++/11/bits/stl_multimap.h \
999
+ /usr/include/c++/11/mutex \
1000
+ /usr/include/c++/11/chrono \
1001
+ /usr/include/c++/11/ratio \
1002
+ /usr/include/c++/11/ctime \
1003
+ /usr/include/c++/11/bits/parse_numbers.h \
1004
+ /usr/include/c++/11/bits/std_mutex.h \
1005
+ /usr/include/c++/11/bits/unique_lock.h \
1006
+ /usr/include/c++/11/set \
1007
+ /usr/include/c++/11/bits/stl_set.h \
1008
+ /usr/include/c++/11/bits/stl_multiset.h \
1009
+ /content/tmp/ggml/src/ggml-cuda/ssm-scan.cuh \
1010
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
1011
+ /content/tmp/ggml/src/../include/ggml.h \
1012
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
1013
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
1014
+ /content/tmp/ggml/src/../include/gguf.h \
1015
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
1016
+ /content/tmp/ggml/src/../include/ggml-backend.h \
1017
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
1018
+ /usr/include/c++/11/memory \
1019
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
1020
+ /usr/include/c++/11/bits/align.h \
1021
+ /usr/include/c++/11/bit \
1022
+ /usr/include/c++/11/bits/unique_ptr.h \
1023
+ /usr/include/c++/11/bits/shared_ptr.h \
1024
+ /usr/include/c++/11/bits/shared_ptr_base.h \
1025
+ /usr/include/c++/11/bits/allocated_ptr.h \
1026
+ /usr/include/c++/11/ext/concurrence.h \
1027
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
1028
+ /usr/include/c++/11/backward/auto_ptr.h \
1029
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
1030
+ /usr/include/c++/11/pstl/execution_defs.h \
1031
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
1032
+ /usr/include/c++/11/cfloat \
1033
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
1034
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
1035
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
1036
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
1037
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
1038
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o.d ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o : /content/tmp/ggml/src/ggml-cuda/sumrows.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/reduce_rows.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/sumrows.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh
ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o.d ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o : /content/tmp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu \
2
+ /usr/include/stdc-predef.h \
3
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime.h \
4
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_config.h \
5
+ /usr/include/features.h \
6
+ /usr/include/features-time64.h \
7
+ /usr/include/x86_64-linux-gnu/bits/wordsize.h \
8
+ /usr/include/x86_64-linux-gnu/bits/timesize.h \
9
+ /usr/include/x86_64-linux-gnu/sys/cdefs.h \
10
+ /usr/include/x86_64-linux-gnu/bits/long-double.h \
11
+ /usr/include/x86_64-linux-gnu/gnu/stubs.h \
12
+ /usr/include/x86_64-linux-gnu/gnu/stubs-64.h \
13
+ /usr/local/cuda/targets/x86_64-linux/include/builtin_types.h \
14
+ /usr/local/cuda/targets/x86_64-linux/include/device_types.h \
15
+ /usr/local/cuda/targets/x86_64-linux/include/crt/host_defines.h \
16
+ /usr/include/ctype.h \
17
+ /usr/include/x86_64-linux-gnu/bits/types.h \
18
+ /usr/include/x86_64-linux-gnu/bits/typesizes.h \
19
+ /usr/include/x86_64-linux-gnu/bits/time64.h \
20
+ /usr/include/x86_64-linux-gnu/bits/endian.h \
21
+ /usr/include/x86_64-linux-gnu/bits/endianness.h \
22
+ /usr/include/x86_64-linux-gnu/bits/types/locale_t.h \
23
+ /usr/include/x86_64-linux-gnu/bits/types/__locale_t.h \
24
+ /usr/local/cuda/targets/x86_64-linux/include/driver_types.h \
25
+ /usr/local/cuda/targets/x86_64-linux/include/vector_types.h \
26
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/limits.h \
27
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/syslimits.h \
28
+ /usr/include/limits.h \
29
+ /usr/include/x86_64-linux-gnu/bits/libc-header-start.h \
30
+ /usr/include/x86_64-linux-gnu/bits/posix1_lim.h \
31
+ /usr/include/x86_64-linux-gnu/bits/local_lim.h \
32
+ /usr/include/linux/limits.h \
33
+ /usr/include/x86_64-linux-gnu/bits/pthread_stack_min-dynamic.h \
34
+ /usr/include/x86_64-linux-gnu/bits/posix2_lim.h \
35
+ /usr/include/x86_64-linux-gnu/bits/xopen_lim.h \
36
+ /usr/include/x86_64-linux-gnu/bits/uio_lim.h \
37
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stddef.h \
38
+ /usr/local/cuda/targets/x86_64-linux/include/surface_types.h \
39
+ /usr/local/cuda/targets/x86_64-linux/include/texture_types.h \
40
+ /usr/local/cuda/targets/x86_64-linux/include/library_types.h \
41
+ /usr/local/cuda/targets/x86_64-linux/include/channel_descriptor.h \
42
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_runtime_api.h \
43
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_device_runtime_api.h \
44
+ /usr/include/c++/11/stdlib.h \
45
+ /usr/include/c++/11/cstdlib \
46
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++config.h \
47
+ /usr/include/x86_64-linux-gnu/c++/11/bits/os_defines.h \
48
+ /usr/include/x86_64-linux-gnu/c++/11/bits/cpu_defines.h \
49
+ /usr/include/c++/11/pstl/pstl_config.h \
50
+ /usr/include/stdlib.h \
51
+ /usr/include/x86_64-linux-gnu/bits/waitflags.h \
52
+ /usr/include/x86_64-linux-gnu/bits/waitstatus.h \
53
+ /usr/include/x86_64-linux-gnu/bits/floatn.h \
54
+ /usr/include/x86_64-linux-gnu/bits/floatn-common.h \
55
+ /usr/include/x86_64-linux-gnu/sys/types.h \
56
+ /usr/include/x86_64-linux-gnu/bits/types/clock_t.h \
57
+ /usr/include/x86_64-linux-gnu/bits/types/clockid_t.h \
58
+ /usr/include/x86_64-linux-gnu/bits/types/time_t.h \
59
+ /usr/include/x86_64-linux-gnu/bits/types/timer_t.h \
60
+ /usr/include/x86_64-linux-gnu/bits/stdint-intn.h \
61
+ /usr/include/endian.h \
62
+ /usr/include/x86_64-linux-gnu/bits/byteswap.h \
63
+ /usr/include/x86_64-linux-gnu/bits/uintn-identity.h \
64
+ /usr/include/x86_64-linux-gnu/sys/select.h \
65
+ /usr/include/x86_64-linux-gnu/bits/select.h \
66
+ /usr/include/x86_64-linux-gnu/bits/types/sigset_t.h \
67
+ /usr/include/x86_64-linux-gnu/bits/types/__sigset_t.h \
68
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timeval.h \
69
+ /usr/include/x86_64-linux-gnu/bits/types/struct_timespec.h \
70
+ /usr/include/x86_64-linux-gnu/bits/select2.h \
71
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes.h \
72
+ /usr/include/x86_64-linux-gnu/bits/thread-shared-types.h \
73
+ /usr/include/x86_64-linux-gnu/bits/pthreadtypes-arch.h \
74
+ /usr/include/x86_64-linux-gnu/bits/atomic_wide_counter.h \
75
+ /usr/include/x86_64-linux-gnu/bits/struct_mutex.h \
76
+ /usr/include/x86_64-linux-gnu/bits/struct_rwlock.h \
77
+ /usr/include/alloca.h \
78
+ /usr/include/x86_64-linux-gnu/bits/stdlib-bsearch.h \
79
+ /usr/include/x86_64-linux-gnu/bits/stdlib-float.h \
80
+ /usr/include/x86_64-linux-gnu/bits/stdlib.h \
81
+ /usr/include/c++/11/bits/std_abs.h \
82
+ /usr/local/cuda/targets/x86_64-linux/include/driver_functions.h \
83
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.h \
84
+ /usr/local/cuda/targets/x86_64-linux/include/vector_functions.hpp \
85
+ /usr/local/cuda/targets/x86_64-linux/include/crt/common_functions.h \
86
+ /usr/include/string.h \
87
+ /usr/include/strings.h \
88
+ /usr/include/x86_64-linux-gnu/bits/strings_fortified.h \
89
+ /usr/include/x86_64-linux-gnu/bits/string_fortified.h \
90
+ /usr/include/time.h \
91
+ /usr/include/x86_64-linux-gnu/bits/time.h \
92
+ /usr/include/x86_64-linux-gnu/bits/timex.h \
93
+ /usr/include/x86_64-linux-gnu/bits/types/struct_tm.h \
94
+ /usr/include/x86_64-linux-gnu/bits/types/struct_itimerspec.h \
95
+ /usr/include/c++/11/new \
96
+ /usr/include/c++/11/bits/exception.h \
97
+ /usr/include/stdio.h \
98
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdarg.h \
99
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos_t.h \
100
+ /usr/include/x86_64-linux-gnu/bits/types/__mbstate_t.h \
101
+ /usr/include/x86_64-linux-gnu/bits/types/__fpos64_t.h \
102
+ /usr/include/x86_64-linux-gnu/bits/types/__FILE.h \
103
+ /usr/include/x86_64-linux-gnu/bits/types/FILE.h \
104
+ /usr/include/x86_64-linux-gnu/bits/types/struct_FILE.h \
105
+ /usr/include/x86_64-linux-gnu/bits/types/cookie_io_functions_t.h \
106
+ /usr/include/x86_64-linux-gnu/bits/stdio_lim.h \
107
+ /usr/include/x86_64-linux-gnu/bits/stdio.h \
108
+ /usr/include/x86_64-linux-gnu/bits/stdio2.h \
109
+ /usr/include/assert.h \
110
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.h \
111
+ /usr/include/c++/11/math.h \
112
+ /usr/include/c++/11/cmath \
113
+ /usr/include/c++/11/bits/cpp_type_traits.h \
114
+ /usr/include/c++/11/ext/type_traits.h \
115
+ /usr/include/math.h \
116
+ /usr/include/x86_64-linux-gnu/bits/math-vector.h \
117
+ /usr/include/x86_64-linux-gnu/bits/libm-simd-decl-stubs.h \
118
+ /usr/include/x86_64-linux-gnu/bits/flt-eval-method.h \
119
+ /usr/include/x86_64-linux-gnu/bits/fp-logb.h \
120
+ /usr/include/x86_64-linux-gnu/bits/fp-fast.h \
121
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-helper-functions.h \
122
+ /usr/include/x86_64-linux-gnu/bits/mathcalls.h \
123
+ /usr/include/x86_64-linux-gnu/bits/mathcalls-narrow.h \
124
+ /usr/include/x86_64-linux-gnu/bits/iscanonical.h \
125
+ /usr/include/c++/11/bits/specfun.h \
126
+ /usr/include/c++/11/bits/stl_algobase.h \
127
+ /usr/include/c++/11/bits/functexcept.h \
128
+ /usr/include/c++/11/bits/exception_defines.h \
129
+ /usr/include/c++/11/ext/numeric_traits.h \
130
+ /usr/include/c++/11/bits/stl_pair.h \
131
+ /usr/include/c++/11/bits/move.h \
132
+ /usr/include/c++/11/type_traits \
133
+ /usr/include/c++/11/bits/stl_iterator_base_types.h \
134
+ /usr/include/c++/11/bits/stl_iterator_base_funcs.h \
135
+ /usr/include/c++/11/bits/concept_check.h \
136
+ /usr/include/c++/11/debug/assertions.h \
137
+ /usr/include/c++/11/bits/stl_iterator.h \
138
+ /usr/include/c++/11/bits/ptr_traits.h \
139
+ /usr/include/c++/11/debug/debug.h \
140
+ /usr/include/c++/11/bits/predefined_ops.h \
141
+ /usr/include/c++/11/limits \
142
+ /usr/include/c++/11/tr1/gamma.tcc \
143
+ /usr/include/c++/11/tr1/special_function_util.h \
144
+ /usr/include/c++/11/tr1/bessel_function.tcc \
145
+ /usr/include/c++/11/tr1/beta_function.tcc \
146
+ /usr/include/c++/11/tr1/ell_integral.tcc \
147
+ /usr/include/c++/11/tr1/exp_integral.tcc \
148
+ /usr/include/c++/11/tr1/hypergeometric.tcc \
149
+ /usr/include/c++/11/tr1/legendre_function.tcc \
150
+ /usr/include/c++/11/tr1/modified_bessel_func.tcc \
151
+ /usr/include/c++/11/tr1/poly_hermite.tcc \
152
+ /usr/include/c++/11/tr1/poly_laguerre.tcc \
153
+ /usr/include/c++/11/tr1/riemann_zeta.tcc \
154
+ /usr/local/cuda/targets/x86_64-linux/include/crt/math_functions.hpp \
155
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.h \
156
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_functions.hpp \
157
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.h \
158
+ /usr/local/cuda/targets/x86_64-linux/include/device_atomic_functions.hpp \
159
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.h \
160
+ /usr/local/cuda/targets/x86_64-linux/include/crt/device_double_functions.hpp \
161
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.h \
162
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_atomic_functions.hpp \
163
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.h \
164
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_atomic_functions.hpp \
165
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_atomic_functions.h \
166
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.h \
167
+ /usr/local/cuda/targets/x86_64-linux/include/sm_60_atomic_functions.hpp \
168
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.h \
169
+ /usr/local/cuda/targets/x86_64-linux/include/sm_20_intrinsics.hpp \
170
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.h \
171
+ /usr/local/cuda/targets/x86_64-linux/include/sm_30_intrinsics.hpp \
172
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.h \
173
+ /usr/local/cuda/targets/x86_64-linux/include/sm_32_intrinsics.hpp \
174
+ /usr/local/cuda/targets/x86_64-linux/include/sm_35_intrinsics.h \
175
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.h \
176
+ /usr/local/cuda/targets/x86_64-linux/include/sm_61_intrinsics.hpp \
177
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.h \
178
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_70_rt.hpp \
179
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.h \
180
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_80_rt.hpp \
181
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.h \
182
+ /usr/local/cuda/targets/x86_64-linux/include/crt/sm_90_rt.hpp \
183
+ /usr/local/cuda/targets/x86_64-linux/include/texture_indirect_functions.h \
184
+ /usr/local/cuda/targets/x86_64-linux/include/surface_indirect_functions.h \
185
+ /usr/local/cuda/targets/x86_64-linux/include/crt/cudacc_ext.h \
186
+ /usr/local/cuda/targets/x86_64-linux/include/device_launch_parameters.h \
187
+ /usr/include/c++/11/functional \
188
+ /usr/include/c++/11/bits/stl_function.h \
189
+ /usr/include/c++/11/backward/binders.h \
190
+ /usr/include/c++/11/tuple \
191
+ /usr/include/c++/11/utility \
192
+ /usr/include/c++/11/bits/stl_relops.h \
193
+ /usr/include/c++/11/initializer_list \
194
+ /usr/include/c++/11/array \
195
+ /usr/include/c++/11/bits/range_access.h \
196
+ /usr/include/c++/11/bits/uses_allocator.h \
197
+ /usr/include/c++/11/bits/invoke.h \
198
+ /usr/include/c++/11/bits/functional_hash.h \
199
+ /usr/include/c++/11/bits/hash_bytes.h \
200
+ /usr/include/c++/11/bits/refwrap.h \
201
+ /usr/include/c++/11/bits/std_function.h \
202
+ /usr/include/c++/11/typeinfo \
203
+ /usr/include/c++/11/unordered_map \
204
+ /usr/include/c++/11/bits/allocator.h \
205
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++allocator.h \
206
+ /usr/include/c++/11/ext/new_allocator.h \
207
+ /usr/include/c++/11/bits/memoryfwd.h \
208
+ /usr/include/c++/11/ext/alloc_traits.h \
209
+ /usr/include/c++/11/bits/alloc_traits.h \
210
+ /usr/include/c++/11/bits/stl_construct.h \
211
+ /usr/include/c++/11/ext/aligned_buffer.h \
212
+ /usr/include/c++/11/bits/hashtable.h \
213
+ /usr/include/c++/11/bits/hashtable_policy.h \
214
+ /usr/include/c++/11/bits/enable_special_members.h \
215
+ /usr/include/c++/11/bits/node_handle.h \
216
+ /usr/include/c++/11/bits/unordered_map.h \
217
+ /usr/include/c++/11/bits/erase_if.h \
218
+ /usr/include/c++/11/vector \
219
+ /usr/include/c++/11/bits/stl_uninitialized.h \
220
+ /usr/include/c++/11/bits/stl_vector.h \
221
+ /usr/include/c++/11/bits/stl_bvector.h \
222
+ /usr/include/c++/11/bits/vector.tcc \
223
+ /usr/include/c++/11/bits/stl_algo.h \
224
+ /usr/include/c++/11/bits/algorithmfwd.h \
225
+ /usr/include/c++/11/bits/stl_heap.h \
226
+ /usr/include/c++/11/bits/stl_tempbuf.h \
227
+ /usr/include/c++/11/bits/uniform_int_dist.h \
228
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-mma-f16.cuh \
229
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../common.cuh \
230
+ /content/tmp/ggml/src/../include/ggml.h \
231
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdbool.h \
232
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/stdint.h \
233
+ /usr/include/stdint.h \
234
+ /usr/include/x86_64-linux-gnu/bits/wchar.h \
235
+ /usr/include/x86_64-linux-gnu/bits/stdint-uintn.h \
236
+ /content/tmp/ggml/src/ggml-cuda/../ggml-impl.h \
237
+ /content/tmp/ggml/src/../include/gguf.h \
238
+ /content/tmp/ggml/src/../include/ggml-cuda.h \
239
+ /content/tmp/ggml/src/../include/ggml-backend.h \
240
+ /content/tmp/ggml/src/../include/ggml-alloc.h \
241
+ /usr/include/c++/11/cstdint \
242
+ /usr/include/c++/11/memory \
243
+ /usr/include/c++/11/bits/stl_raw_storage_iter.h \
244
+ /usr/include/c++/11/bits/align.h \
245
+ /usr/include/c++/11/bit \
246
+ /usr/include/c++/11/bits/unique_ptr.h \
247
+ /usr/include/c++/11/bits/shared_ptr.h \
248
+ /usr/include/c++/11/iosfwd \
249
+ /usr/include/c++/11/bits/stringfwd.h \
250
+ /usr/include/c++/11/bits/postypes.h \
251
+ /usr/include/c++/11/cwchar \
252
+ /usr/include/wchar.h \
253
+ /usr/include/x86_64-linux-gnu/bits/types/wint_t.h \
254
+ /usr/include/x86_64-linux-gnu/bits/types/mbstate_t.h \
255
+ /usr/include/x86_64-linux-gnu/bits/wchar2.h \
256
+ /usr/include/c++/11/bits/shared_ptr_base.h \
257
+ /usr/include/c++/11/bits/allocated_ptr.h \
258
+ /usr/include/c++/11/ext/atomicity.h \
259
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr.h \
260
+ /usr/include/x86_64-linux-gnu/c++/11/bits/gthr-default.h \
261
+ /usr/include/pthread.h \
262
+ /usr/include/sched.h \
263
+ /usr/include/x86_64-linux-gnu/bits/sched.h \
264
+ /usr/include/x86_64-linux-gnu/bits/types/struct_sched_param.h \
265
+ /usr/include/x86_64-linux-gnu/bits/cpu-set.h \
266
+ /usr/include/x86_64-linux-gnu/bits/setjmp.h \
267
+ /usr/include/x86_64-linux-gnu/bits/types/struct___jmp_buf_tag.h \
268
+ /usr/include/x86_64-linux-gnu/c++/11/bits/atomic_word.h \
269
+ /usr/include/x86_64-linux-gnu/sys/single_threaded.h \
270
+ /usr/include/c++/11/ext/concurrence.h \
271
+ /usr/include/c++/11/exception \
272
+ /usr/include/c++/11/bits/exception_ptr.h \
273
+ /usr/include/c++/11/bits/cxxabi_init_exception.h \
274
+ /usr/include/c++/11/bits/nested_exception.h \
275
+ /usr/include/c++/11/bits/shared_ptr_atomic.h \
276
+ /usr/include/c++/11/bits/atomic_base.h \
277
+ /usr/include/c++/11/bits/atomic_lockfree_defines.h \
278
+ /usr/include/c++/11/backward/auto_ptr.h \
279
+ /usr/include/c++/11/pstl/glue_memory_defs.h \
280
+ /usr/include/c++/11/pstl/execution_defs.h \
281
+ /content/tmp/ggml/src/ggml-cuda/../ggml-common.h \
282
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.h \
283
+ /usr/local/cuda/targets/x86_64-linux/include/nv/target \
284
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__target_macros \
285
+ /usr/local/cuda/targets/x86_64-linux/include/nv/detail/__preprocessor \
286
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp16.hpp \
287
+ /usr/include/c++/11/cassert \
288
+ /usr/include/c++/11/cfloat \
289
+ /usr/lib/gcc/x86_64-linux-gnu/11/include/float.h \
290
+ /usr/include/c++/11/cstdio \
291
+ /usr/include/c++/11/string \
292
+ /usr/include/c++/11/bits/char_traits.h \
293
+ /usr/include/c++/11/bits/localefwd.h \
294
+ /usr/include/x86_64-linux-gnu/c++/11/bits/c++locale.h \
295
+ /usr/include/c++/11/clocale \
296
+ /usr/include/locale.h \
297
+ /usr/include/x86_64-linux-gnu/bits/locale.h \
298
+ /usr/include/c++/11/cctype \
299
+ /usr/include/c++/11/bits/ostream_insert.h \
300
+ /usr/include/c++/11/bits/cxxabi_forced.h \
301
+ /usr/include/c++/11/bits/basic_string.h \
302
+ /usr/include/c++/11/string_view \
303
+ /usr/include/c++/11/bits/string_view.tcc \
304
+ /usr/include/c++/11/ext/string_conversions.h \
305
+ /usr/include/c++/11/cerrno \
306
+ /usr/include/errno.h \
307
+ /usr/include/x86_64-linux-gnu/bits/errno.h \
308
+ /usr/include/linux/errno.h \
309
+ /usr/include/x86_64-linux-gnu/asm/errno.h \
310
+ /usr/include/asm-generic/errno.h \
311
+ /usr/include/asm-generic/errno-base.h \
312
+ /usr/include/x86_64-linux-gnu/bits/types/error_t.h \
313
+ /usr/include/c++/11/bits/charconv.h \
314
+ /usr/include/c++/11/bits/basic_string.tcc \
315
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vendors/cuda.h \
316
+ /usr/local/cuda/targets/x86_64-linux/include/cuda.h \
317
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_v2.h \
318
+ /usr/local/cuda/targets/x86_64-linux/include/cublas_api.h \
319
+ /usr/local/cuda/targets/x86_64-linux/include/cuComplex.h \
320
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.h \
321
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_bf16.hpp \
322
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.h \
323
+ /usr/local/cuda/targets/x86_64-linux/include/cuda_fp8.hpp \
324
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../cp-async.cuh \
325
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../mma.cuh \
326
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../fattn-common.cuh \
327
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../convert.cuh \
328
+ /content/tmp/ggml/src/ggml-cuda/template-instances/../vecdotq.cuh