[FIX_FOR_VLLM_CUSTOM=0a54df28471be07b3d668ea21c5e411569d3baea] Fix DynamicNTKScalingRotaryEmbedding and HPUCompressedTensorsConfig#1479
Merged
iboiko-habana merged 1 commit intoMay 22, 2026
Conversation
…or upstream vllm@0a54df28 Root cause: Upstream vLLM PRs #41277 and #43144 changed APIs in DynamicNTKScalingRotaryEmbedding (added max_trained_positions) and CompressedTensorsConfig (removed sparsity params). Upstream: vllm-project/vllm#41277, vllm-project/vllm#43144 Fix: Add max_trained_positions to rotary embedding test; remove stale sparsity_scheme_map and sparsity_ignore_list from HPUCompressedTensorsConfig init. Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com>
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
temporarily deployed
to
pre-merge-approval
GitHub Actions
Inactive
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
This PR appears to remove sparsity-compression configuration plumbing from the Gaudi compressed-tensors path and updates a rotary-embedding unit test to include a max_trained_positions field.
Changes:
- Removed
SparsityCompressionConfigimport and sparsity-related__init__parameters/forwarding inhpu_compressed_tensors.py. - Updated rotary-embedding test config to include
max_trained_positions.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| vllm_gaudi/ops/hpu_compressed_tensors.py | Drops sparsity config types and constructor parameters from the HPU compressed-tensors integration. |
| tests/unit_tests/ops/test_hpu_rotary_embedding.py | Adds max_trained_positions to the test configuration for dynamic NTK scaling. |
✅ CI PassedAll checks passed successfully against the following vllm commit: |
iboiko-habana
approved these changes
May 22, 2026
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.
Root cause
Upstream vLLM at SHA 0a54df28 introduced two API changes that broke vllm-gaudi:
max_trained_positionsparameter toDynamicNTKScalingRotaryEmbedding.__init__(), causing the unit test to fail with TypeError.sparsity_scheme_mapandsparsity_ignore_listfromCompressedTensorsConfig.__init__(), causingHPUCompressedTensorsConfiginstantiation to fail during e2e tests.Upstream PR
vllm-project/vllm#41277
Added max_trained_positions to DynamicNTKScalingRotaryEmbedding
vllm-project/vllm#43144
Removed sparsity parameters from CompressedTensorsConfig
Fix
max_trained_positionsparameter to the rotary embedding unit test.sparsity_scheme_mapandsparsity_ignore_listfrom HPUCompressedTensorsConfig init signature and super() call, plus the unused SparsityCompressionConfig import.