Revert PTA upgrade PR (#3352)

we notice that torch npu 0919 doesn't work. This PR revert related
change which rely on 0919 version.
Revert PR: #3295  #3205  #3102 

Related: #3353

- vLLM version: v0.11.0

vllm_ascend/utils.py

@@ -501,7 +501,8 @@ def register_ascend_customop(vllm_config: Optional[VllmConfig] = None):
     from vllm_ascend.ops.activation import AscendQuickGELU, AscendSiluAndMul
     from vllm_ascend.ops.common_fused_moe import (AscendFusedMoE,
                                                   AscendSharedFusedMoE)
-    from vllm_ascend.ops.layernorm import AscendGemmaRMSNorm, AscendRMSNorm
+    from vllm_ascend.ops.layernorm import (AscendGemmaRMSNorm,
+                                           AscendQuantRMSNorm, AscendRMSNorm)
     from vllm_ascend.ops.linear import (AscendColumnParallelLinear,
                                         AscendMergedColumnParallelLinear,
                                         AscendQKVParallelLinear,
@@ -532,6 +533,11 @@ def register_ascend_customop(vllm_config: Optional[VllmConfig] = None):
         "MultiHeadLatentAttention": AscendMultiHeadLatentAttention,
     }
 
+    if vllm_config is not None and \
+        vllm_config.quant_config is not None and \
+        any("norm.bias" in name for name in vllm_config.quant_config.quant_description.keys()):
+        REGISTERED_ASCEND_OPS["RMSNorm"] = AscendQuantRMSNorm
+
     for name, op_cls in REGISTERED_ASCEND_OPS.items():
         CustomOp.register_oot(_decorated_op_cls=op_cls, name=name)