[main][Feature] Support deepseek w4a8 quantization (#2172)

### What this PR does / why we need it?
Supports Deepseek-R1 w4a8 quantization.
Since R1 w4a8 uses mixed quantization, only the MOE layer uses
w4a8_dynamic quantization, so we added the w4a8_dynamic.py file, which
includes the AscendW4A8DynamicFusedMoEMethod class.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
Adding ut case in `tests/ut/quantization/test_w4a8_dynamic.py` and
`tests/ut/quantization/test_quantizer.py`
Adding e2e case in
`tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC`
to test deepseek w4a8_dynamic quantized model

#### 1.How to get weights using Modelslim
##### Installation steps
Use the branch master, the commit id is:
298e175d69b3b855111a1e09bbe2fcd12fdb4e24
git clone https://gitee.com/ascend/msit.git
cd msit/msmodelslim
bash install.sh

##### The required transformers environment
transformers>=4.48.2

##### Generate w4a8 weights
cd /example/DeepSeek
Command reference: msmodelslim/example/DeepSeek/README.md Execute the
[pre-check](https://gitee.com/ascend/msit/blob/master/msmodelslim/example/DeepSeek/README.md#%E8%BF%90%E8%A1%8C%E5%89%8D%E5%BF%85%E6%A3%80)
and [DeepSeek-R1 w4a8 mix
quantization](https://gitee.com/ascend/msit/blob/master/msmodelslim/example/DeepSeek/README.md#deepseek-r1-w4a8-%E6%B7%B7%E5%90%88%E9%87%8F%E5%8C%96%E5%89%8D%E4%B8%89%E5%B1%82-mlpw8a8-dynamic-%E9%87%8F%E5%8C%96mla%E5%85%B1%E4%BA%AB%E4%B8%93%E5%AE%B6w8a8%E9%87%8F%E5%8C%96%E8%B7%AF%E7%94%B1%E4%B8%93%E5%AE%B6w4a8-dynamic%E9%87%8F%E5%8C%96)
chapter
Reference command：python3 quant_deepseek_w4a8.py --model_path {Original
weight path} --save_path {Generate weight path} --mindie_format

##### Adapt to vllm-ascend
Since mindie_format generates mindie format, some adaptation
modifications are needed for vllm-ascend to use it:
`quant_model_description_w8a8_dynamic.json` rename to
`quant_model_description.json`, and add `"group_size": 256`
Modification in `config.json`：`"model_type":deepseekv2` is changed to
`"model_type":deepseek_v3`; `quantization_config` is removed;
tips:The group_size and weights match. If the w4a8 weights are not
generated using msmodelslim, you can check the group_size in
quantization_config in config.json.

#### 2.How to run w4a8
##### a.How to run eager mode
export VLLM_USE_V1=1 # v1

python -m vllm.entrypoints.openai.api_server --model=$1
--trust-remote-code -tp $2 -dp $3 --enable_expert_parallel
--quantization ascend --port $4 --max-model-len $5 --max-num-seqs $6
--enforce-eager
eg: python -m vllm.entrypoints.openai.api_server
--model=/weightpath/w4a8_4_layer --trust-remote-code -tp 4 -dp 4
--enable_expert_parallel --quantization ascend --port 8002
--max-model-len 5120 --max-num-seqs 128 --enforce-eager

##### b.How to run graph mode
export VLLM_USE_V1=1 # v1
export HCCL_BUFFSIZE=1024

python -m vllm.entrypoints.openai.api_server --model=$1
--trust-remote-code -tp $2 -dp $3 --enable_expert_parallel
--quantization ascend --port $4 --max-model-len $5
--additional_config='{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true}}'
eg: python -m vllm.entrypoints.openai.api_server
--model=/weight/dsr1_w4a8_vllm --trust-remote-code -tp 4 -dp 4
--enable_expert_parallel --quantization ascend --port 8002
--max-model-len 5120
--additional_config='{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true}}'


- vLLM version: v0.10.0
- vLLM main:
c494f96fbc

---------

Signed-off-by: Wang Kunpeng <1289706727@qq.com>

vllm_ascend/quantization/quantizer.py

@@ -24,7 +24,8 @@ from vllm.logger import logger
 
 from .func_wrapper import (wrapper_rmsnorm_forward_oot, wrapper_rmsnorm_init,
                            wrapper_vocab_parallel_embedding_init)
-from .w4a8_dynamic import AscendW4A8DynamicLinearMethod
+from .w4a8_dynamic import (AscendW4A8DynamicFusedMoEMethod,
+                           AscendW4A8DynamicLinearMethod)
 from .w8a8 import (AscendC8KVCacheMethod, AscendW8A8FusedMoEMethod,
                    AscendW8A8LinearMethod)
 from .w8a8_dynamic import (AscendW8A8DynamicFusedMoEMethod,
@@ -97,12 +98,15 @@ class VLLMAscendQuantizer:
         if target_function is not None:
             setattr(original_module, target_function, candidate)
 
-        for key, value in sys.modules.copy().items():
-            if (target_function is not None
-                    and hasattr(value, target_function)
-                    and id(getattr(value,
-                                   target_function)) == original_function_id):
-                setattr(value, target_function, candidate)
+        for _, value in sys.modules.copy().items():
+            if target_function is None:
+                continue
+            try:
+                attr = getattr(value, target_function, None)
+                if attr is not None and id(attr) == original_function_id:
+                    setattr(value, target_function, candidate)
+            except ImportError:
+                continue
 
     @staticmethod
     def parse_path(module_path, function_name, create_dummy):
@@ -268,6 +272,10 @@ class W4A8DYNAMICQuantizer(VLLMAscendQuantizer):
     def build_linear_method():
         return AscendW4A8DynamicLinearMethod()
 
+    @staticmethod
+    def build_moe_method():
+        return AscendW4A8DynamicFusedMoEMethod()
+
 
 class W8A8Quantizer(VLLMAscendQuantizer):