[main][Feature] Support Qwen3 W4A8 quantization (#2060)

### What this PR does / why we need it?

Adding `W4A8_DYNAMIC` quantization support for linear.
Dense models like Qwen3 can infer with `W4A8_DYNAMIC` quantization.

### Does this PR introduce _any_ user-facing change?

None

### How was this patch tested?

Adding ut case in `tests/ut/quantization/test_w4a8_dynamic.py`
Adding e2e case in
`tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC`
to test qwen3 w4a8_dynamic quantized model

Note the w4a8_dynamic quantized model is quantized by `msit/msmodelslim`
of commit `d0abb0a47e1f1a473b866ad41b737fbc28fb1409`

1. Generate `W4A8_DYNAMIC` quantization weights using `msmodelslim`
```shell
git clone https://gitee.com/ascend/msit.git
cd msit/msmodelslim
git checkout d0abb0a47e1f1a473b866ad41b737fbc28fb1409
bash install.sh
```

2. Serve model using `vllm`
```shell
VLLM_USE_V1=1 python -m vllm.entrypoints.openai.api_server \
  --model vllm-ascend/Qwen3-8B-W4A8 \
  --port 8000 \
  --quantization ascend \
  --tensor_parallel_size 2 \
  --enforce-eager
```

- vLLM version: v0.10.0
- vLLM main:
4cd7fe6cea

---------

Signed-off-by: ZhouXiang <zhouxiang100@huawei.com>

vllm_ascend/quantization/quant_config.py

@@ -205,6 +205,17 @@ class AscendLinearMethod(LinearMethodBase):
             layer.register_parameter(perchannel_name, param)
             set_weight_attrs(param, extra_weight_attrs)
 
+        pergroup_dict = self.quant_method.get_pergroup_param(
+            input_size_per_partition, output_size_per_partition, params_dtype)
+        for pergroup_name, pergroup_param in pergroup_dict.items():
+            param = torch.nn.Parameter(pergroup_param, requires_grad=False)
+            set_weight_attrs(param, {"output_dim": 0})
+            layer.register_parameter(pergroup_name, param)
+            set_weight_attrs(param, extra_weight_attrs)
+            if "weight_scale_second" in pergroup_name or "weight_offset_second" in pergroup_name:
+                setattr(param, "input_dim", 1)
+                param.input_dim = 1
+
     def process_weights_after_loading(self, layer: torch.nn.Module) -> None:
         if hasattr(self.quant_method, "process_weights_after_loading"):
             self.quant_method.process_weights_after_loading(layer)