hotfix - Revert vllm/attention/layer.py changes from 0f8cafe - fix torch.compile recompilations #709
Conversation
This file contains 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
… torch.compile recompilations
RafLit
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski,
mgawarkiewicz,
vivekgoe and
afierka-intel
as code owners
anko-intel
approved these changes
Jan 23, 2025
This was referenced Jan 23, 2025
anko-intel
changed the title
anko-intel
reviewed
Jan 24, 2025
Comment on lines
+139
to
+142
| if self.use_direct_call: | ||
| return self.impl.forward(query, key, value, kv_cache, | ||
| attn_metadata, self._k_scale, | ||
| self._v_scale) |
There was a problem hiding this comment.
Could we add only those lines and left the rest unattached?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
0f8cafe change from upstream modified the Attention vllm layer to use unified_attention which uses self.layer_name for layer device dispatch. This causes recompilations as each layer has a different name.