sunxin c29e86fc9d [Feature] Support mtp overlap schedule (#7001)

2026-04-01 14:24:26 +08:00

..

ops

[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

__init__.py

…

early_stopper.py

…

logprobs.py

[Feature] Support mtp overlap schedule (#7001)

2026-04-01 14:24:26 +08:00

meta_data.py

[BugFix] Fix mtp when token_ids_all is None (#6591)

2026-03-02 01:23:44 -08:00

sampler.py

[Feature] Support mtp overlap schedule (#7001)

2026-04-01 14:24:26 +08:00