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

Bump to 2.5.9

Browse Source
This commit is contained in:
Tri Dao 2024-05-26 14:02:11 -07:00
parent d732be1e67
commit ce73503578
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
flash_attn/__init__.py
View File

@ -1,4 +1,4 @@
__version__ = "2.5.8"
__version__ = "2.5.9"
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==2.5.8
RUN pip install flash-attn==2.5.9
# Install CUDA extensions for fused dense
RUN pip install git+https://github.com/HazyResearch/flash-attention@v2.5.8#subdirectory=csrc/fused_dense_lib
RUN pip install git+https://github.com/HazyResearch/flash-attention@v2.5.9#subdirectory=csrc/fused_dense_lib