[attention backends] change to updated repo and version.#13161
Open
[attention backends] change to updated repo and version.#13161
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
danieldk
reviewed
Feb 18, 2026
| # TODO: temporary revision for now. Remove when merged upstream into `main`. | ||
| AttentionBackendName._FLASH_3_HUB: _HubKernelConfig( | ||
| repo_id="kernels-community/flash-attn3", function_attr="flash_attn_func", revision="fake-ops-return-probs" | ||
| repo_id="kernels-community/flash-attn3", function_attr="flash_attn_func", revision="v1" |
Member
There was a problem hiding this comment.
Suggested change
| repo_id="kernels-community/flash-attn3", function_attr="flash_attn_func", revision="v1" | |
| repo_id="kernels-community/flash-attn3", function_attr="flash_attn_func", version=1 |
with kernels >= 0.12
Member
Author
There was a problem hiding this comment.
Are we then asking the users to always keep kernels to >=0.12? Personally, I don't have a problem with it, just want to make sure we're on the same page.
| ), | ||
| AttentionBackendName.SAGE_HUB: _HubKernelConfig( | ||
| repo_id="kernels-community/sage_attention", function_attr="sageattn", revision=None | ||
| repo_id="kernels-community/sage-attention", function_attr="sageattn", revision=None |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
For standardization.
@danieldk @drbh could you advise the
revisionwe should use in diffusers for the attention backends? I have only changed the FA3 one in this PR.