[Feat][quantization] Support new version w4a8 dynamic quantization for Linear layers

[Anionex]

What this PR does / why we need it?

Problem Description:

The existing implementation for the w4a8-dynamic linear method only supports the old quantization format from msmodelslim. When attempting to load models quantized with the new version, vLLM encounters errors due to mismatched tensor shapes and unprocessed quantization parameters.

Relavant issues:

• 这代码是有问题的，如果weight的output_dim不是8的倍数，就会报错 #3192
• 这里计算scale_bias的方式和msit中不一致，可能存在问题 #3152

Proposed Changes:

1. Add support for w4a8 dynamic(new format) in AscendW4A8DynamicLinearMethod and TorchairAscendW4A8DynamicLinearMethod
2. Add unit tests and e2e tests for w4a8 dynamic new and old format models

details

1. Support for new w4a8-dynamic format:

   • Detects quantization format by reading the "version" field in quant_description to ensure backward compatibility.
   • Handles the new pre-packed weight format (2x int4 in an int8), which has a halved dimension. It tells the vLLM loader how to unpack it using _packed_dim and _packed_factor.
   • Supports the new scale_bias parameter, setting its shape based on the layer type, as required by msmodelslim. For api consistency and future use, the layer_type parameter was also added to other quantization methods.
   • Updates the weight processing logic: new format weights are handled with .view(torch.int32) since they're pre-packed, while old ones are processed with npu_convert_weight_to_int4pack.

2. New unit and E2E tests:

   • Added unit tests that verify the logic for both the old and new formats.
   • Split the distributed E2E test to confirm that both old and new format models work correctly.

Theoretically, these changes will provide support for all common new version w4a8(dynamic) models from msmodelslim.

Does this PR introduce any user-facing change?

no

How was this patch tested?

I implement relevant unit tests and e2e tests and test the changes with following commands:

# unit tests
python -m pytest tests/ut/quantization/test_w4a8_dynamic.py tests/ut/torchair/quantization/test_torchair_w4a8_dynamic.py -v

# e2e tests
pytest tests/e2e/singlecard/test_quantization.py -v -s

pytest tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC_new_version -v -s
pytest tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC_old_version -v -s
pytest tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC -v -s

I also tested Hunyuan-1.8B-Instruct quantized with the new w4a8-dynamic format:

vllm serve ./models/Hunyuan-1.8B-Instruct-quantized --gpu-memory-utilization 0.96 --quantization ascend --max-model-len 9600 --seed 0 --max-num-batched-tokens 16384 

All tests mentioned passed locally.

NOTE: I use quantization model from my own repo in test_offline_inference_distributed.py. Here is the description: Anionex/Qwen3-1.7B-W4A8-V1 (including quantization steps).This should be replaced by a model in vllm-ascend ci modelscope repo.

Thanks for reading!

• vLLM version: v0.11.0rc3
• vLLM main: vllm-project/vllm@releases/v0.11.0

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[Anionex]

Hi maintainers,
It seems that the failed ci test errors in ascend test / full / e2e-full (releases/v0.11.0) is the same:

TypeError: CustomDeepseekV2DecoderLayer.__init__() takes 3 positional arguments but 4 were given

, which is unrelated to this pr.
(I noted that https://github.com/vllm-project/vllm-ascend/actions/runs/18274504364/job/52023422660 also encountered this error)

Could you please help skip this test? Or do you have any other advice? Thank you
cc: @Yikun