GGUF
conversational
HelloSun commited on
Commit
73fbc37
·
verified ·
1 Parent(s): cb84020

Upload opt/prof_decode.txt with huggingface_hub

Browse files
Files changed (1) hide show
  1. opt/prof_decode.txt +12 -0
opt/prof_decode.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ "avg_ts": 32.210311
2
+ PROF total compute 3571.2 ms, barrier-wait 353.2 ms
3
+ PROF ADD n= 26316 compute 34.30 ms barrier 18.01 ms (1.3 us/op compute, 0.7 us/op barrier)
4
+ PROF RMS_NORM n= 8901 compute 0.35 ms barrier 3.25 ms (0.0 us/op compute, 0.4 us/op barrier)
5
+ PROF GET_ROWS n= 387 compute 0.61 ms barrier 0.19 ms (1.6 us/op compute, 0.5 us/op barrier)
6
+ PROF SET_ROWS n= 8772 compute 11.75 ms barrier 5.78 ms (1.3 us/op compute, 0.7 us/op barrier)
7
+ PROF ROPE n= 8772 compute 12.65 ms barrier 22.85 ms (1.4 us/op compute, 2.6 us/op barrier)
8
+ PROF FLASH_ATTN_EXT n= 4386 compute 82.19 ms barrier 13.96 ms (18.7 us/op compute, 3.2 us/op barrier)
9
+ PROF GLU n= 4386 compute 40.82 ms barrier 3.01 ms (9.3 us/op compute, 0.7 us/op barrier)
10
+ PROF MUL_MAT q4_K n= 26316 compute 2470.86 ms barrier 236.91 ms (93.9 us/op compute, 9.0 us/op barrier)
11
+ PROF MUL_MAT q6_K n= 4515 compute 917.64 ms barrier 49.19 ms (203.2 us/op compute, 10.9 us/op barrier)
12
+ PROF_DONE