backport of v0.9.1-dev:
https://github.com/vllm-project/vllm-ascend/pull/1902
origin main npu_moe_gating_top_k_softmax:
https://github.com/vllm-project/vllm-ascend/pull/1355
- vLLM version: v0.10.0
- vLLM main:
055bd3978e
Signed-off-by: huangxialu <huangxialu1@huawei.com>