[Feat] 310p support MoE W8A8 quantizaition (#6641)

### What this PR does / why we need it?
This PR introduces support for W8A8 dynamic quantization for
Mixture-of-Experts (MoE) models on Ascend 310P devices. This is achieved
by:
- Implementing a new quantization scheme
`AscendW8A8DynamicFusedMoEMethod310`.
- Adding a unified MLP implementation (`unified_apply_mlp`) for 310P
that handles both quantized and unquantized paths.
- Refactoring the MoE and quantization configuration logic to correctly
route to the new 310P-specific implementations.
- Adding new e2e and unit tests to verify the functionality of MoE W8A8
quantization.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
- Added a new e2e test `test_qwen3_moe_tp2_w8a8` to test MoE W8A8
quantization in a multi-card setup.
- Added several new unit tests for the 310P-specific MoE components,
including `experts_selector`, `fused_moe`, `moe_comm_method`, `moe_mlp`,
and the new `w8a8_dynamic` quantization method.

- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

---------

Signed-off-by: pu-zhe <zpuaa@outlook.com>

vllm_ascend/_310p/fused_moe/experts_selector.py

@@ -19,7 +19,6 @@ from collections.abc import Callable
 import torch
 
 from vllm_ascend.ops.fused_moe.experts_selector import _native_select_experts
-from vllm_ascend.utils import get_weight_prefetch_method
 
 
 def select_experts(
@@ -55,9 +54,6 @@ def select_experts(
         topk_weights: router weights of shape (num_tokens, top_k).
         topk_ids: selected expert IDs of shape (num_tokens, top_k).
     """
-    # prefetch w1_w3_proj.weight preprocess
-    weight_prefetch_method = get_weight_prefetch_method()
-    weight_prefetch_method.maybe_prefetch_moe_weight_preprocess(hidden_states, "gate_up")
     topk_weights, topk_ids = _native_select_experts(
         hidden_states=hidden_states,
         router_logits=router_logits,