[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

### What this PR does / why we need it?
1.qwen3 moe uses add_rms_norm_quant op instead of 'add_rms_norm op and
quant op' during quantization scene.
2.torch_npu.add_rms_norm_quant op fixed accuracy while model weights is
quantized by anti_method m4, m4 quantization is asymmetric outlier
suppression method, it will generate none-zero norm bias,
add_rms_norm_quant op updated to add this parameter to calculate.
3. add torch-npu check

### Does this PR introduce _any_ user-facing change?
new feature works if torch_npu version >= torch_npu-2.7.1.dev20250919

### How was this patch tested?
1.no special parameters to set, no new envs to set. new feature works if
torch_npu version >= torch_npu-2.7.1.dev20250919
2.use qwen3 moe quantization model to test ,such as
Qwen3-235B-A22B-W8A8, Qwen3-30B-A3B-W8A8,
Qwen3-235B-A22B-Instruct-2507-m4 (anti_method m4)

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: h30027576 <huangdong51@huawei.com>

vllm_ascend/attention/attention_v1.py

@@ -33,13 +33,12 @@ from vllm.v1.kv_cache_interface import AttentionSpec
 
 from vllm_ascend.attention.utils import (AscendCommonAttentionMetadata,
                                          maybe_save_kv_layer_to_connector,
-                                         version_check,
                                          wait_for_kv_layer_from_connector)
 from vllm_ascend.compilation.acl_graph import (get_graph_params,
                                                update_graph_params_workspaces)
 from vllm_ascend.ops.attention import vanilla_chunked_prefill
 from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, aligned_16, is_310p,
-                               nd_to_nz_2d, nd_to_nz_spec)
+                               nd_to_nz_2d, nd_to_nz_spec, version_check)
 
 from ..utils import weak_ref_tensors
 

vllm_ascend/attention/utils.py

@@ -1,10 +1,8 @@
-import functools
 from dataclasses import dataclass
 from typing import Any, List
 
 import torch
 import torch.nn.functional as F
-import torch_npu
 from vllm.distributed.kv_transfer import (get_kv_transfer_group,
                                           has_kv_transfer_group,
                                           is_v1_kv_transfer_group)
@@ -142,20 +140,6 @@ def maybe_save_kv_layer_to_connector(
     connector.save_kv_layer(layer_name, kv_cache_layer, attn_metadata)
 
 
-@functools.cache
-def version_check():
-    import re
-    torch_npu_version = torch_npu.version.__version__
-    date_pattern = r'dev(\d{8})'
-
-    match = re.search(date_pattern, torch_npu_version)
-    if match:
-        full_date = match.group(1)
-        if full_date >= "20250919":
-            return True
-    return False
-
-
 def round_up(val: int, align: int) -> int:
     if align == 0:
         return 0