[feature] Support W8A8 PD-Mix Quantization (#4235)

In PD-separated deployment scenarios:

* MoE layers use dynamic quantization exclusively.
* For the Attention module, Prefill (P) nodes use **dynamic**
quantization, while Decode (D) nodes use **static** quantization.

In PD-mixed deployment scenarios:
* **All components fall back to dynamic quantization**, as it is
difficult to distinguish between Prefill and Decode tokens.
___

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
Signed-off-by: Slightwind <slightwindsec@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

vllm_ascend/quantization/utils.py

@@ -12,6 +12,8 @@ from .w8a8 import (AscendC8KVCacheMethod, AscendW8A8FusedMoEMethod,
                    AscendW8A8LinearMethod)
 from .w8a8_dynamic import (AscendW8A8DynamicFusedMoEMethod,
                            AscendW8A8DynamicLinearMethod)
+from .w8a8_pdmix import (AscendW8A8PDMixFusedMoeMethod,
+                         AscendW8A8PDMixLinearMethod)
 
 ASCEND_QUANTIZATION_METHOD_MAP: Dict[str, Dict[str, Type[Any]]] = {
     "W4A8_DYNAMIC": {
@@ -30,6 +32,10 @@ ASCEND_QUANTIZATION_METHOD_MAP: Dict[str, Dict[str, Type[Any]]] = {
         "linear": AscendW8A8DynamicLinearMethod,
         "moe": AscendW8A8DynamicFusedMoEMethod,
     },
+    "W8A8_MIX": {
+        "linear": AscendW8A8PDMixLinearMethod,
+        "moe": AscendW8A8PDMixFusedMoeMethod,
+    },
     "C8": {
         "attention": AscendC8KVCacheMethod,
     },