Skip to content

add snapKV implementation for transformers sdpa attention with flash_attn availability checking#32

Open
Clement25 wants to merge 1 commit into
FasterDecoding:mainfrom
Clement25:main
Open

add snapKV implementation for transformers sdpa attention with flash_attn availability checking#32
Clement25 wants to merge 1 commit into
FasterDecoding:mainfrom
Clement25:main

Enhance your code review process with GitHub Actions

GitHub Actions make it easy to automate all your software workflows, now with world-class CI/CD.
Build, test, and deploy your code right from GitHub. Learn more about GitHub Actions.

Linux, macOS, Windows, and containers
Linux, macOS, Windows, and containers
Matrix builds
Matrix builds
Any language
Any language
Live logs
Live logs
Built-in secret store
Built-in secret store
Multi-container testing
Multi-container testing