[FIX_FOR_VLLM_CUSTOM=d3af8c18317c0dc008d42e4367fbb9045cfb7bf6] Add hf_config parameter to HPU quantization config overrides#1349
Merged
tzielinski-habana merged 2 commits intoApr 15, 2026
Conversation
Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com>
Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com>
pawel-olejniczak
requested review from
PatrykWo,
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
Fixes an upstream-compatibility regression where vLLM now passes hf_config= into override_quantization_method(), causing the Gaudi HPU GPTQ/AWQ plugin implementations (still using the old signature) to raise a TypeError.
Changes:
- Extend
GPTQHPUConfig.override_quantization_method()to accept an optionalhf_configparameter for API compatibility. - Extend
AWQHPUConfig.override_quantization_method()to accept an optionalhf_configparameter for API compatibility. - Re-enable the
build_nixl_dockerfileCI job when the NIXL Dockerfile is modified.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
vllm_gaudi/ops/hpu_gptq.py |
Updates the override hook signature to accept the new upstream hf_config kwarg. |
vllm_gaudi/ops/hpu_awq.py |
Updates the override hook signature to accept the new upstream hf_config kwarg. |
.github/workflows/pre-merge.yaml |
Restores Dockerfile build validation for .cd/Dockerfile.ubuntu.pytorch.vllm.nixl.latest changes. |
iboiko-habana
approved these changes
Apr 14, 2026
✅ CI PassedAll checks passed successfully against the following vllm commit: |
bmyrcha
pushed a commit
to bmyrcha/vllm-gaudi
that referenced
this pull request
Apr 17, 2026
…_config parameter to HPU quantization config overrides (vllm-project#1349) ## Summary Fixes a regression introduced by upstream vLLM that breaks all quantization tests using HPU-specific GPTQ and AWQ backends (e.g. `run_qwen3_inc_dynamic_load_generate_test`). ## Changes 1. **Add `hf_config` parameter to `override_quantization_method()` in `GPTQHPUConfig` and `AWQHPUConfig`** — upstream changed the call site in `vllm/config/model.py` to pass `hf_config=self.hf_config`, but plugin implementations still used the old 2-parameter signature, causing `TypeError`. 2. **Re-enable `build_nixl_dockerfile` CI test** in pre-merge workflow. ## Upstream PR that introduced the regression - vllm-project/vllm#39604 — added `hf_config` keyword argument to `override_quantization_method()` call and updated all upstream implementations, but plugin implementations were not updated. --------- Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com> Signed-off-by: bmyrcha <bartosz.myrcha@intel.com>
yeonsily
pushed a commit
to yeonsily/vllm-gaudi
that referenced
this pull request
Apr 21, 2026
…_config parameter to HPU quantization config overrides (vllm-project#1349) ## Summary Fixes a regression introduced by upstream vLLM that breaks all quantization tests using HPU-specific GPTQ and AWQ backends (e.g. `run_qwen3_inc_dynamic_load_generate_test`). ## Changes 1. **Add `hf_config` parameter to `override_quantization_method()` in `GPTQHPUConfig` and `AWQHPUConfig`** — upstream changed the call site in `vllm/config/model.py` to pass `hf_config=self.hf_config`, but plugin implementations still used the old 2-parameter signature, causing `TypeError`. 2. **Re-enable `build_nixl_dockerfile` CI test** in pre-merge workflow. ## Upstream PR that introduced the regression - vllm-project/vllm#39604 — added `hf_config` keyword argument to `override_quantization_method()` call and updated all upstream implementations, but plugin implementations were not updated. --------- Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com> Signed-off-by: Yeonsil Yoon <yeon.sil.yoon@intel.com>
bmyrcha
pushed a commit
to bmyrcha/vllm-gaudi
that referenced
this pull request
Apr 22, 2026
…_config parameter to HPU quantization config overrides (vllm-project#1349) ## Summary Fixes a regression introduced by upstream vLLM that breaks all quantization tests using HPU-specific GPTQ and AWQ backends (e.g. `run_qwen3_inc_dynamic_load_generate_test`). ## Changes 1. **Add `hf_config` parameter to `override_quantization_method()` in `GPTQHPUConfig` and `AWQHPUConfig`** — upstream changed the call site in `vllm/config/model.py` to pass `hf_config=self.hf_config`, but plugin implementations still used the old 2-parameter signature, causing `TypeError`. 2. **Re-enable `build_nixl_dockerfile` CI test** in pre-merge workflow. ## Upstream PR that introduced the regression - vllm-project/vllm#39604 — added `hf_config` keyword argument to `override_quantization_method()` call and updated all upstream implementations, but plugin implementations were not updated. --------- Signed-off-by: Paweł Olejniczak <pawelx.olejniczak@intel.com> Signed-off-by: bmyrcha <bartosz.myrcha@intel.com>
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.
Summary
Fixes a regression introduced by upstream vLLM that breaks all quantization tests using HPU-specific GPTQ and AWQ backends (e.g.
run_qwen3_inc_dynamic_load_generate_test).Changes
hf_configparameter tooverride_quantization_method()inGPTQHPUConfigandAWQHPUConfig— upstream changed the call site invllm/config/model.pyto passhf_config=self.hf_config, but plugin implementations still used the old 2-parameter signature, causingTypeError.build_nixl_dockerfileCI test in pre-merge workflow.Upstream PR that introduced the regression
hf_configkeyword argument tooverride_quantization_method()call and updated all upstream implementations, but plugin implementations were not updated.