linfeng-yuan 695e5c9ebc [0.11.0][ops] npu_top_k_top_p supports k and p only (#4153) ...

### What this PR does / why we need it?
With CANN 8.3 and corresponding PTA 2.7.1, `npu_top_k_top_p` supports
passing only k (1<=k<=1024) and p separately.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
E2E performance test with only `top_k` and `p` seperately. This pr gains
0.2ms improvements in TPOT with `batch_size=16`.

Signed-off-by: linfeng-yuan <1102311262@qq.com>

2025-12-09 15:45:40 +08:00

..

logits_processor

[main] add pd transfer for ascend scheduler (#2753)

2025-09-10 08:46:39 +08:00

__init__.py

Spec decode support for V1 Engine (#874)

2025-05-23 14:25:46 +08:00

rejection_sampler.py

[Perf][MTP] Optimize reject sampler in greedy situation. (#2137)

2025-08-11 17:37:49 +08:00

sampler.py

[0.11.0][ops] npu_top_k_top_p supports k and p only (#4153)

2025-12-09 15:45:40 +08:00