[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/ops/fused_moe/fused_moe.py

@@ -387,7 +387,7 @@ class AscendFusedMoE(FusedMoE):
 
     def transpose_weight(self, loaded_weight, expert_data, shard_dim):
         # Ensure training and inference weight shapes match during RL weight updates
-        if (
+        if (len(loaded_weight.shape) >= 2 and len(expert_data.shape) >= 2 and \
             loaded_weight.shape[1] != expert_data.shape[1] and \
             loaded_weight.shape[0] != expert_data.shape[0]
         ):