Files
xc-llm-ascend/tests/ut/quantization
1092626063 9328f377b4 [refactor]support gatingtopk operator generalization (#2958)
### What this PR does / why we need it?

Past:
npu_moe_gating_top_k can only support 'group_count=256' pattern

Now:
1、npu_moe_gating_top_k support all size of group_count
2、the functionality of `torch_npu.npu_moe_gating_top_k_softmax` are
included in `torch_npu.npu_moe_gating_top_k`

CANN: depends on 8.3.RC1

Performance:
1. GLM4.5-w8a8, TPS improve 6%
2. Qwen3, the same as before

- vLLM version: v0.11.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/2918c1b49c88c29783c86f78d2c4221cb9622379

Signed-off-by: 1092626063 <1092626063@qq.com>
2025-11-19 10:38:56 +08:00
..