Port of: Fix stale gate ref overriding caller router_logits in dp_size==1 MoE fast path (#1469)#1492
Merged
mgawarkiewicz-intel merged 2 commits intoMay 26, 2026
Conversation
…e==1 MoE fast path (vllm-project#1469) Signed-off-by: Iryna Boiko <iboiko@habana.ai>
iboiko-habana
requested review from
PatrykWo,
mgawarkiewicz-intel and
wpyszka
as code owners
iboiko-habana
had a problem deploying
to
pre-merge-approval
GitHub Actions
Error
Contributor
There was a problem hiding this comment.
Pull request overview
Ports an upstream fix to prevent the dp_size==1 MoE fast path from using a stale cached gate reference after INC conversion, which can override the caller-provided router_logits and trigger shape/dtype mismatches (notably under fp8).
Changes:
- When synchronizing post-INC MoE state, refreshes
runner._hpu_gate_refto point to the post-INC block-level gate whenrunner.gateis cleared.
Comment on lines
+4824
to
+4825
| if block_gate is not None: | ||
| object.__setattr__(runner, "_hpu_gate_ref", block_gate) |
iboiko-habana
temporarily deployed
to
pre-merge-approval
GitHub Actions
Inactive
✅ CI PassedAll checks passed successfully against the following vllm commit: |
kamil-kaczor
approved these changes
May 26, 2026
Collaborator
kamil-kaczor
left a comment
kamil-kaczor
left a comment
There was a problem hiding this comment.
I trust you although Copilot says it's not needed. GL
mgawarkiewicz-intel
merged commit 1dc158d
into
vllm-project:releases/v0.21.0
3 checks passed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.