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

Limit to MAX_JOBS=1 with CUDA 12.2

Browse Source
This commit is contained in:
Tri Dao 2024-05-26 15:35:21 -07:00
parent ce73503578
commit e2e4333c95
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/publish.yml vendored
View File

@ -168,7 +168,8 @@ 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
# Limit MAX_JOBS otherwise the github runner goes OOM
MAX_JOBS=2 FLASH_ATTENTION_FORCE_BUILD="TRUE" FLASH_ATTENTION_FORCE_CXX11_ABI=${{ matrix.cxx11_abi}} python setup.py bdist_wheel --dist-dir=dist
# CUDA 11.8 can compile with 2 jobs, but CUDA 12.2 goes OOM
MAX_JOBS=$([ "$MATRIX_CUDA_VERSION" == "122" ] && echo 1 || echo 2) FLASH_ATTENTION_FORCE_BUILD="TRUE" FLASH_ATTENTION_FORCE_CXX11_ABI=${{ matrix.cxx11_abi}} python setup.py bdist_wheel --dist-dir=dist
tmpname=cu${MATRIX_CUDA_VERSION}torch${MATRIX_TORCH_VERSION}cxx11abi${{ matrix.cxx11_abi }}
wheel_name=$(ls dist/*whl | xargs -n 1 basename | sed "s/-/+$tmpname-/2")
ls dist/*whl |xargs -I {} mv {} dist/${wheel_name}

2
flash_attn/__init__.py
View File

@ -1,4 +1,4 @@
__version__ = "2.5.9"
__version__ = "2.5.9.post1"
from flash_attn.flash_attn_interface import (
flash_attn_func,

4
training/Dockerfile
View File

@ -85,7 +85,7 @@ RUN pip install transformers==4.25.1 datasets==2.8.0 pytorch-lightning==1.8.6 tr
RUN pip install git+https://github.com/mlcommons/logging.git@2.1.0
# Install FlashAttention
RUN pip install flash-attn==2.5.9
RUN pip install flash-attn==2.5.9.post1
# Install CUDA extensions for fused dense
RUN pip install git+https://github.com/HazyResearch/flash-attention@v2.5.9#subdirectory=csrc/fused_dense_lib
RUN pip install git+https://github.com/HazyResearch/flash-attention@v2.5.9.post1#subdirectory=csrc/fused_dense_lib