[Fusion] [Graph]Add Matmul Allreduce Rmsnorm fusion Pass (#5034)

This PR add `MatmulAllreduceRmsnorm` operator and introduces a graph
fusion pass for `matmul_allreduce_rmsnorm` operations. The
implementation includes a new configuration flag, a pattern matching
pass using `torch._inductor.pattern_matcher`.

Co-authored-by: Trunrain [270250579@qq.com](mailto:270250579@qq.com)

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: tongrunze <t00574058@china.huawei.com>

vllm_ascend/compilation/graph_fusion_pass_manager.py

@@ -58,3 +58,8 @@ class GraphFusionPassManager:
             from .passes.qknorm_rope_fusion_pass import QKNormRopeFusionPass
 
             self.passes.append(QKNormRopeFusionPass(config))
+
+        if self.ascend_compilation_config.get("fuse_allreduce_rms", True):
+            from .passes.allreduce_rmsnorm_fusion_pass import MatmulAllReduceAddRMSNormPass
+
+            self.passes.append(MatmulAllReduceAddRMSNormPass(config))