Refactor AscendMultiHeadLatentAttention (#2826)

### What this PR does / why we need it?
Register AscendMultiHeadLatentAttention as CustomOP, following vllm changes

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.


- vLLM version: main
- vLLM main:
b23fb78623

---------

Signed-off-by: Icey <1790571317@qq.com>

vllm_ascend/utils.py

@@ -529,6 +529,10 @@ def register_ascend_customop():
     from vllm_ascend.ops.common_fused_moe import AscendFusedMoE
     CustomOp.register_oot(_decorated_op_cls=AscendFusedMoE, name="FusedMoE")
 
+    from vllm_ascend.models.layers.mla import AscendMultiHeadLatentAttention
+    CustomOp.register_oot(_decorated_op_cls=AscendMultiHeadLatentAttention,
+                          name="MultiHeadLatentAttention")
+
     # NOTE: Keep this at last to ensure all custom actions are registered
     _ASCEND_CUSTOMOP_IS_REIGISTERED = True