theroyallab/tabbyAPI
1
0
Fork 0
mirror of https://github.com/theroyallab/tabbyAPI.git synced 2026-03-14 15:57:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Requirements: Update Flash Attention 2

Browse Source 
Bump to 2.3.6

Signed-off-by: kingbri <bdashore3@proton.me>
This commit is contained in:
kingbri
2023-12-03 01:56:29 -05:00
parent c67c9f6d66
commit e740b53478
1 changed files with 4 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
requirements.txt
View File

@@ -9,17 +9,9 @@ uvicorn
# Flash Attention 2. If the wheels don't work, comment these out, uncomment the old wheels, and run `pip install -r requirements.txt`
# Windows FA2 from https://github.com/jllllll/flash-attention/releases
https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# Linux FA2 from https://github.com/Dao-AILab/flash-attention/releases
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# Old flash attention 2 wheels. Uncomment these and if the new ones don't work!
# IMPORTANT: Make sure to re-comment the new wheels before re-running `pip install -r requirements.txt`
# https://github.com/bdashore3/flash-attention/releases/download/2.3.3/flash_attn-2.3.3+cu122-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
# https://github.com/bdashore3/flash-attention/releases/download/2.3.3/flash_attn-2.3.3+cu122-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.3/flash_attn-2.3.3+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
# https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.3/flash_attn-2.3.3+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"