[MISC] Clean up torch_npu (#688)

torch_npu 2.5.1 support autoload now. This patch does:
1. remove useless torch_npu import
2. replace `torch_npu.npu` to `torch.npu`.

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/quantization/quant_config.py

@@ -19,7 +19,6 @@ from types import MappingProxyType
 from typing import Any, Callable, Dict, List, Mapping, Optional
 
 import torch
-import torch_npu  # noqa: F401
 from vllm.distributed import get_tensor_model_parallel_rank
 from vllm.model_executor.layers.fused_moe import (FusedMoE, FusedMoEMethodBase,
                                                   FusedMoeWeightScaleSupported)