upgrade torch npu version (#4433)

vLLM graph feature now rely on torch >=2.8. To make graph mode work, we
need upgrade torch version as well. For long term support, upgrade torch
to a newer one is good to go as well.

Related vLLM change: https://github.com/vllm-project/vllm/pull/25110


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

vllm_ascend/attention/mla_v1.py

@@ -924,8 +924,10 @@ class AscendMLAImpl(MLAAttentionImpl):
         def get_layer_weight(layer):
             WEIGHT_NAMES = ("weight", "qweight", "weight_packed")
             for attr in WEIGHT_NAMES:
-                if hasattr(layer, attr):
+                try:
                     return getattr(layer, attr)
+                except AttributeError:
+                    pass
             raise AttributeError(
                 f"Layer '{layer}' has no recognized weight attribute:"
                 f" {WEIGHT_NAMES}.")