[FIX_FOR_VLLM_CUSTOM=dc6de33c3d5e9026cef7b27791dfe0f98e64bbde] Hourly fixes – batch no. 2#998
Merged
iboiko-habana merged 4 commits intovllm-project:mainfrom Feb 23, 2026
Conversation
Signed-off-by: Paweł Olejniczak <polejniczakx@habana.ai>
Signed-off-by: Paweł Olejniczak <polejniczakx@habana.ai>
pawel-olejniczak
requested review from
adobrzyn,
afierka-intel,
iboiko-habana,
kamil-kaczor,
ksmusz,
mgawarkiewicz-intel,
michalkuligowski and
xuechendi
as code owners
Contributor
There was a problem hiding this comment.
Pull request overview
This pull request includes hourly automated fixes for the vLLM HPU (Habana Processing Unit) integration. The changes address two issues: adding a missing quant_method property delegation in the HPU LoRA implementation, and implementing a custom create_fused_moe_router factory function for HPU-specific MoE routing.
Changes:
- Added
quant_methodproperty toHPUVocabParallelEmbeddingWithLoRAto delegate to the base layer - Implemented
create_fused_moe_routerfactory function with support for multiple router types and patched it into vllm modules
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| vllm_gaudi/ops/hpu_lora.py | Adds quant_method property delegation to fix AttributeError when accessing quantization methods on HPU LoRA layers |
| vllm_gaudi/ops/hpu_fused_moe.py | Adds router factory function with imports and patches to support various MoE routing strategies on HPU |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
iboiko-habana
approved these changes
Feb 20, 2026
Signed-off-by: Paweł Olejniczak <polejniczakx@habana.ai>
✅ 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.
This PR contains part of fixes from #903
Fixed issues:
AttributeError: '_OpNamespace' '_moe_C' object has no attribute 'topk_softmax'
AttributeError: 'HPUVocabParallelEmbeddingWithLoRA' object has no attribute 'quant_method'