sunxin 33e01f22a8 [Feature][Sampling] Extend top-k_top-p sampling to all backends and unify greedy decoding with top_k=1 (#6894) ...

* update sampling

* fix

* fix

* fix mtp

* fix test

2026-03-19 01:43:10 -07:00

..

__init__.py

[Feature]Support tag phase token enforce generation (#6034)

2026-01-15 03:59:55 -08:00

apply_penalty_multi_scores.py

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407)

2026-02-28 15:07:43 +08:00

speculate_logprob_utils.py

[Feature] support mtp logprob (#4464)

2025-10-20 15:18:12 +08:00

top_k_top_p_sampling.py

[Feature][Sampling] Extend top-k_top-p sampling to all backends and unify greedy decoding with top_k=1 (#6894)

2026-03-19 01:43:10 -07:00