thanks to nerfacc ❤

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+py310_cu118/nerfacc_cuda/nerfacc_cuda.so filter=lfs diff=lfs merge=lfs -text
+py310_cu118/segment_cumsum_cuda/segment_cumsum.o filter=lfs diff=lfs merge=lfs -text
+py310_cu118/segment_cumsum_cuda/segment_cumsum_cuda.so filter=lfs diff=lfs merge=lfs -text

py310_cu118/nerfacc_cuda/.ninja_log

@@ -0,0 +1,7 @@
+# ninja log v5
+1	249135	1698960090552008807	pdf.cuda.o	b778e71794e36552
+1	249850	1698960091271075369	scan.cuda.o	c4e4720afa0f0ba6
+1	250896	1698960092287169425	grid.cuda.o	29686952940e9c80
+249850	298345	1698960139782565895	nerfacc.o	2be0a519e2b43e1
+249135	361260	1698960202688388658	camera.cuda.o	d2c7e45a63cc1c22
+361260	362020	1698960203447458911	nerfacc_cuda.so	de654c7d7fc303c6

py310_cu118/nerfacc_cuda/build.ninja

@@ -0,0 +1,37 @@
+ninja_required_version = 1.3
+cxx = c++
+nvcc = /usr/local/cuda/bin/nvcc
+
+cflags = -DTORCH_EXTENSION_NAME=nerfacc_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/TH -isystem /usr/local/lib/python3.10/dist-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /usr/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -O3
+post_cflags = 
+cuda_cflags = -DTORCH_EXTENSION_NAME=nerfacc_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/TH -isystem /usr/local/lib/python3.10/dist-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /usr/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_75,code=compute_75 -gencode=arch=compute_75,code=sm_75 --compiler-options '-fPIC' -O3 -std=c++17
+cuda_post_cflags = 
+cuda_dlink_post_cflags = 
+ldflags = -shared -L/usr/local/lib/python3.10/dist-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/usr/local/cuda/lib64 -lcudart
+
+rule compile
+  command = $cxx -MMD -MF $out.d $cflags -c $in -o $out $post_cflags
+  depfile = $out.d
+  deps = gcc
+
+rule cuda_compile
+  depfile = $out.d
+  deps = gcc
+  command = $nvcc  $cuda_cflags -c $in -o $out $cuda_post_cflags
+
+
+
+rule link
+  command = $cxx $in $ldflags -o $out
+
+build grid.cuda.o: cuda_compile /usr/local/lib/python3.10/dist-packages/nerfacc/cuda/csrc/grid.cu
+build scan.cuda.o: cuda_compile /usr/local/lib/python3.10/dist-packages/nerfacc/cuda/csrc/scan.cu
+build pdf.cuda.o: cuda_compile /usr/local/lib/python3.10/dist-packages/nerfacc/cuda/csrc/pdf.cu
+build camera.cuda.o: cuda_compile /usr/local/lib/python3.10/dist-packages/nerfacc/cuda/csrc/camera.cu
+build nerfacc.o: compile /usr/local/lib/python3.10/dist-packages/nerfacc/cuda/csrc/nerfacc.cpp
+
+
+
+build nerfacc_cuda.so: link grid.cuda.o scan.cuda.o pdf.cuda.o camera.cuda.o nerfacc.o
+
+default nerfacc_cuda.so

py310_cu118/nerfacc_cuda/nerfacc_cuda.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305922e04a0c55591ccf4a00c05b757bbf72f73c3c9c2aefa976d17619a66d95
+size 1693800

py310_cu118/segment_cumsum_cuda/.ninja_log

@@ -0,0 +1,4 @@
+# ninja log v5
+0	34971	1698960239322779245	segment_cumsum.o	5fe9ca4b5490cde8
+0	97760	1698960302101589553	segment_cumsum_kernel.cuda.o	c79c4ca27eb3b605
+97760	98613	1698960302959668970	segment_cumsum_cuda.so	e20db84fad1fa9d5

py310_cu118/segment_cumsum_cuda/build.ninja

@@ -0,0 +1,34 @@
+ninja_required_version = 1.3
+cxx = c++
+nvcc = /usr/local/cuda/bin/nvcc
+
+cflags = -DTORCH_EXTENSION_NAME=segment_cumsum_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/TH -isystem /usr/local/lib/python3.10/dist-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /usr/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17
+post_cflags = 
+cuda_cflags = -DTORCH_EXTENSION_NAME=segment_cumsum_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/TH -isystem /usr/local/lib/python3.10/dist-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /usr/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_75,code=compute_75 -gencode=arch=compute_75,code=sm_75 --compiler-options '-fPIC' -std=c++17
+cuda_post_cflags = 
+cuda_dlink_post_cflags = 
+ldflags = -shared -L/usr/local/lib/python3.10/dist-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/usr/local/cuda/lib64 -lcudart
+
+rule compile
+  command = $cxx -MMD -MF $out.d $cflags -c $in -o $out $post_cflags
+  depfile = $out.d
+  deps = gcc
+
+rule cuda_compile
+  depfile = $out.d
+  deps = gcc
+  command = $nvcc  $cuda_cflags -c $in -o $out $cuda_post_cflags
+
+
+
+rule link
+  command = $cxx $in $ldflags -o $out
+
+build segment_cumsum.o: compile /usr/local/lib/python3.10/dist-packages/torch_efficient_distloss/cuda/segment_cumsum.cpp
+build segment_cumsum_kernel.cuda.o: cuda_compile /usr/local/lib/python3.10/dist-packages/torch_efficient_distloss/cuda/segment_cumsum_kernel.cu
+
+
+
+build segment_cumsum_cuda.so: link segment_cumsum.o segment_cumsum_kernel.cuda.o
+
+default segment_cumsum_cuda.so

py310_cu118/segment_cumsum_cuda/segment_cumsum.o

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7564b7d9602bb466c892f411a796f7af5bd381603b22fb6c22a756ccb7c8a648
+size 1808368

py310_cu118/segment_cumsum_cuda/segment_cumsum_cuda.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88a4177bb2daea1fd20bcb1e81685d65b91c542016cf79dd20f3a8693ecf250
+size 1451296