Enable qwen3 vl moe quant and load #1182
Open
+258
−6
Conversation
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
…fp UT Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
for more information, see https://pre-commit.ci
Contributor
There was a problem hiding this comment.
Pull request overview
This PR enables quantization and loading support for the Qwen3-VL-MoE model by implementing expert-to-linear conversion and adding comprehensive test coverage.
Key Changes:
- Added Qwen3-VL-MoE model handler with expert conversion logic similar to existing MoE models
- Implemented device-aware E2M1 tensor caching to improve performance
- Added test fixtures and test cases for both CPU and CUDA environments
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| auto_round/modelling/qwen3_vl_moe.py | New module implementing LinearQwen3VLMoeTextSparseMoeBlock for expert-to-linear conversion during quantization |
| auto_round/special_model_handler.py | Registered qwen3_vl_moe in supported models list and expert conversion mapping |
| test/test_cuda/test_moe_model.py | Added fixture and test case for Qwen3-VL-MoE MXFP4 quantization on CUDA |
| test/test_cpu/test_moe_model.py | Added fixture and test case for Qwen3-VL-MoE MXFP4 quantization on CPU |
| auto_round/experimental/qmodules/fp4_utils.py | Refactored E2M1 lookup tensor to use device-aware caching mechanism |
| auto_round/data_type/utils.py | Added trailing newline for consistency |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
…auto-round into enable_qwen3_vl_moe_quant
Co-authored-by: Yi Liu <yi4.liu@intel.com>
Co-authored-by: Yi Liu <yi4.liu@intel.com>
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.
No description provided.