-
Notifications
You must be signed in to change notification settings - Fork 100
fix default window size for sparse_attn #39
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Signed-off-by: Minmin Sun <[email protected]>
@minminsun Sorry for the confusion but we will be making the (we had to do this this |
Hi @LucasWilkinson This PR is a bug fix for sparse_attn. It's OK for me to make the PR to branch lwilkinson/fa3-squashed, but I found that sparse_attn is not in that branch yet. Can we merge thie PR to main branch first, and, after that, cherry-pick the sparse_attn along with this change to that branch? |
hmmm it should be: https://github.com/vllm-project/flash-attention/blob/lwilkinson/fa3-squashed/csrc/flash_attn/flash_api_sparse.cpp sorry its just in its own file now to reduce the diff with upstream |
OK, I See. I will file another PR to the new branch. And I think the current main also needs this fix before it gets replaced. |
Main is deprecated now, ill try to make sure the renaming happens next week 👍 we were just hesitant since we've been busy with the V1 and DeepSeek pushes so didn't want to break anything during such a crazy time, apologies |
Apologies for the inconvenience, please update this PR to point to the new |
Signed-off-by: Mike Lasby <[email protected]>
Signed-off-by: Mike Lasby <[email protected]>
Signed-off-by: Mike Lasby <[email protected]> Co-authored-by: Mike Lasby <[email protected]>
No description provided.