[FIX_FOR_VLLM_CUSTOM=b06813e87207e15b133e903d641e03f237d85b17] Fix gdn_linear_attn import path after upstream mamba refactor#1496
Merged
adobrzyn merged 1 commit intoMay 27, 2026
Conversation
pawel-olejniczak
requested review from
PatrykWo,
adobrzyn,
afierka-intel,
iboiko-habana,
jbyczkow,
kamil-kaczor,
ksmusz,
mgawarkiewicz-intel,
michalkuligowski and
xuechendi
as code owners
pawel-olejniczak
had a problem deploying
to
pre-merge-approval
GitHub Actions
Error
…n_linear_attn import path after upstream mamba refactor Root cause: upstream vLLM PR #41126 (7e1b45a092) refactored gdn_linear_attn.GatedDeltaNetAttention into a gdn/ subpackage: vllm.model_executor.layers.mamba.gdn.qwen_gdn_linear_attn.QwenGatedDeltaNetAttention Fix: Update import paths and class references in qwen3_5.py to match the new upstream module structure. Replace GatedDeltaNetAttention with QwenGatedDeltaNetAttention in the monkey-patch targets. Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com>
pawel-olejniczak
force-pushed
the
fix/gdn-linear-attn-import-path
branch
from
ba51ad7 to
838e3d2
Compare
pawel-olejniczak
temporarily deployed
to
pre-merge-approval
GitHub Actions
Inactive
pawel-olejniczak
temporarily deployed
to
pre-merge-approval
GitHub Actions
Inactive
✅ 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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Root cause
Upstream vLLM PR vllm-project/vllm#41126 (commit 7e1b45a092) refactored
vllm.model_executor.layers.mamba.gdn_linear_attn.GatedDeltaNetAttentioninto a
gdn/subpackage:vllm.model_executor.layers.mamba.gdn.qwen_gdn_linear_attn.QwenGatedDeltaNetAttention.This broke
vllm_gaudi/models/qwen3_5.pywhich imported from the old path.Fix
Updated 6 lines in
vllm_gaudi/models/qwen3_5.py:gdn_linear_attntogdn.qwen_gdn_linear_attnGatedDeltaNetAttentiontoQwenGatedDeltaNetAttentionUpstream compatibility
Pinned to vLLM SHA:
b06813e87207e15b133e903d641e03f237d85b17