squall/flash-attention
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[CI] Fix MATRIX_CUDA_VERSION check

Browse Source
This commit is contained in:
Tri Dao 2023-08-14 10:27:26 -07:00
parent 9c531bdc0a
commit f8dccfc90a
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/publish.yml vendored
View File

@ -142,7 +142,7 @@ jobs:
export PATH=/usr/local/nvidia/bin:/usr/local/nvidia/lib64:$PATH
export LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:$LD_LIBRARY_PATH
# Currently for this setting the runner goes OOM if we pass --threads 4 to nvcc
if [[ ${MATRIX_CUDA_VERSION} == "12.1" && ${MATRIX_TORCH_VERSION} == "2.1" ]]; then
if [[ ${MATRIX_CUDA_VERSION} == "121" && ${MATRIX_TORCH_VERSION} == "2.1" ]]; then
export FLASH_ATTENTION_FORCE_SINGLE_THREAD="TRUE"
fi
# Limit MAX_JOBS otherwise the github runner goes OOM

2
flash_attn/__init__.py
View File

@ -1,4 +1,4 @@
__version__ = "2.0.6.post1"
__version__ = "2.0.6.post2"
from flash_attn.flash_attn_interface import flash_attn_func
from flash_attn.flash_attn_interface import flash_attn_kvpacked_func