Merged
Conversation
Signed-off-by: Xin He <xin3.he@intel.com>
Signed-off-by: Xin He <xin3.he@intel.com>
Signed-off-by: Xin He <xin3.he@intel.com>
Signed-off-by: Xin He <xin3.he@intel.com>
xin3he
requested review from
Kaihui-intel,
WeiweiZhang1,
XuehaoSun and
Copilot
and removed request for
Copilot
Signed-off-by: Xin He <xin3.he@intel.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates AutoRound’s CUDA-focused unit tests and a small part of the AutoGPTQ export path to restore test stability against newer dependency combinations (notably transformers), and to make a few tests less environment-dependent.
Changes:
- Gate Phi-3.5 VLM CUDA tests behind a
transformers<4.54.0constraint due to upstream model incompatibility. - Adjust CUDA tests to use
require_gptqmodeland switch AutoScheme tests toquantize_and_save(...)for export + evaluation. - Add a BF16 → FP32 conversion for
zpin AutoGPTQ packing and tweak missing-tensor logging.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| test/test_cuda/models/test_support_vlms.py | Skips Phi-3.5 VLM tests on newer transformers where the model is known incompatible. |
| test/test_cuda/export/test_auto_gptq_format.py | Uses require_gptqmodel instead of require_optimum for AutoGPTQ-format tests. |
| test/test_cuda/algorithms/test_auto_scheme.py | Quantize + save in export tests so accuracy evaluation runs against saved artifacts. |
| test/test_cpu/integrations/test_llmc_integration.py | Disables torch compile in LLMC recipes and uses a tiny local TinyLlama fixture for oneshot. |
| test/conftest.py | Changes GGUF invalid-version workaround to set __version__ to 0.10.0. |
| auto_round/utils/missing_tensors.py | Adjusts log formatting for “missing tensors copied” message. |
| auto_round/export/export_to_autogptq/export.py | Converts BF16 zp tensor to FP32 before packing to avoid dtype issues. |
Contributor
Author
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
chensuyue
approved these changes
Mar 24, 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.
Description
Type of Change
Related Issues
Fixes or relates to #1471
Checklist Before Submitting