Skip to content
This repository was archived by the owner on Feb 3, 2026. It is now read-only.

1 runtimeerror flashattention only supports ampere gpus or newer#62

Open
zhanwenchen wants to merge 5 commits intomagic-research:mainfrom
zhanwenchen:1-runtimeerror-flashattention-only-supports-ampere-gpus-or-newer
Open

1 runtimeerror flashattention only supports ampere gpus or newer#62
zhanwenchen wants to merge 5 commits intomagic-research:mainfrom
zhanwenchen:1-runtimeerror-flashattention-only-supports-ampere-gpus-or-newer

Conversation

@zhanwenchen
Copy link

No description provided.

@zhanwenchen zhanwenchen marked this pull request as draft June 6, 2024 21:41
@zhanwenchen zhanwenchen marked this pull request as ready for review July 28, 2024 18:45
@zhanwenchen
Copy link
Author

zhanwenchen commented Jul 28, 2024

@ermu2001 This PR fixes the V100 flash_attn-related errors from #1

update default system prompt in demo
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants