cherry pick Llama4 on apply patches + QK flatten pos + perf drop#942
Merged
wpyszka merged 1 commit intoFeb 9, 2026
Merged
Conversation
Signed-off-by: Luca Calabria <luca.calabria@intel.com>
Luca-Calabria
requested review from
mgawarkiewicz-intel,
piotrbocian and
wpyszka
as code owners
Contributor
There was a problem hiding this comment.
Pull request overview
This PR cherry-picks Llama4 fixes from PRs #881, #862, and #884 onto the releases branch. The changes focus on improving the Llama4 attention scale calculation and refactoring model-specific patches.
Changes:
- Refactored
_get_attn_scale_for_hputo directly implement attention scale logic instead of wrapping original method - Moved
maybe_set_chunked_attention_layersfrom instance method to module-level function - Updated
apply_model_specific_patchesto acceptmodel_runnerinstead ofmodelparameter
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+423
to
+428
| for layer in model_runner.model.language_model.model.layers: | ||
| if "ChunkedLocalAttention" in layer.self_attn.attn.get_attn_backend().__name__: | ||
| layer.self_attn.attn.impl.is_chunked_attention = True | ||
| except Exception: | ||
| # add explicit warning | ||
| pass |
There was a problem hiding this comment.
The comment indicates a warning should be added, but the exception handler silently passes. Either add the intended warning message or remove the misleading comment.
adobrzyn
approved these changes
Feb 6, 2026
jkaniecki
approved these changes
Feb 6, 2026
✅ CI PassedAll checks passed successfully against the following vllm commit: |
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
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.
Cherry pick Llama4 missing fixes from #881 #862 #884 on releases/ branch