add mxfp8 moe quantization (#6670)

### What this PR does / why we need it?
support mxfp8 quantization (Qwen MOE )
Using adaptor to make the hardware-specific behavior clearer and more
maintainable
### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
13397841ab

---------

Signed-off-by: fangrongcan <17343701736@163.com>
Signed-off-by: wangyao-i <iwangyao@outlook.com>
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: Eric-dot <60131170+Eric-dot@users.noreply.github.com>
Co-authored-by: fangrongcan <f00876277@china.huawei.com>
Co-authored-by: wangyao-i <iwangyao@outlook.com>
Co-authored-by: linfeng-yuan <1102311262@qq.com>

vllm_ascend/ascend_forward_context.py

@@ -264,6 +264,11 @@ def select_moe_comm_method(num_tokens: int, vllm_config: VllmConfig, is_draft_mo
             moe_comm_type = MoECommType.FUSED_MC2 if fused_prefill_enable else MoECommType.ALLTOALL
     elif soc_version in {AscendDeviceType._310P}:
         moe_comm_type = MoECommType.ALLGATHER
+    elif soc_version in {AscendDeviceType.A5}:
+        if num_tokens <= mc2_tokens_capacity and vllm_config.parallel_config.world_size_across_dp > 1:
+            moe_comm_type = MoECommType.MC2
+        else:
+            moe_comm_type = MoECommType.ALLTOALL
     else:
         raise ValueError(f"Unsupported soc_version: {soc_version}")
     return moe_comm_type