ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] FMHA FWD bug fix (#2888)

Browse Source 
* tempsave debug

* fix the bug in fmha fwd_kernel

* Remove unnecessary changes

* Fix the buggy part

* remove fmha fwd known failure cases
This commit is contained in:
Haocong WANG
2025-09-23 15:00:46 +08:00
committed by GitHub
parent ad259eeae2
commit b6e8994386
3 changed files with 24 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
example/ck_tile/01_fmha/script/fmha_fwd_known_fails_gfx950.txt
View File

@@ -1,4 +0,0 @@
tile_example_fmha_fwd -prec=fp16 -mode=0 -b=2 -h=1 -d=128 -d_v=24 -s=3 -s_k=99 -bias=n -p_drop=0.0 -lse=0 -iperm=0 -operm=0 -mask=2 -num_splits=1 -page_block_size=0 -cache_batch_idx=0 -kname=1 -v=1 -warmup=0 -repeat=1
tile_example_fmha_fwd -prec=fp16 -mode=0 -b=1 -h=2 -h_k=1 -d=128 -s=1 -s_k=10 -s_kpad=32 -bias=n -p_drop=0.0 -lse=0 -iperm=0 -operm=0 -mask=2 -num_splits=1 -page_block_size=0 -cache_batch_idx=0 -kname=1 -v=1 -warmup=0 -repeat=1
tile_example_fmha_fwd -prec=fp16 -mode=0 -b=2 -h=1 -d=128 -d_v=24 -s=3 -s_k=99 -bias=n -p_drop=0.0 -lse=0 -iperm=1 -operm=1 -mask=2 -num_splits=1 -page_block_size=0 -cache_batch_idx=0 -kname=1 -v=1 -warmup=0 -repeat=1
tile_example_fmha_fwd -prec=fp16 -mode=0 -b=1 -h=2 -h_k=1 -d=128 -s=1 -s_k=10 -s_kpad=32 -bias=n -p_drop=0.0 -lse=0 -iperm=1 -operm=1 -mask=2 -num_splits=1 -page_block_size=0 -cache_batch_idx=0 -kname=1 -v=1 -warmup=0 -repeat=1