Myeongwon Kim 8977ea8895 [Perf] Skip detokenization in offline beam search (#50333) ...

Signed-off-by: samuelkim7 <samuelmwkim@gmail.com>

2026-08-10 16:17:38 -07:00

..

base

[Feature] Parse request priority from HTTP header (#51089)

2026-08-05 21:10:29 -07:00

beam_search

[Perf] Skip detokenization in offline beam search (#50333)

2026-08-10 16:17:38 -07:00

generative_scoring

[Frontend] Refine the entrypoint class's inheritance hierarchy. (#47498)

2026-07-03 10:50:06 +00:00

__init__.py

[Frontend] Consolidate beam search by BeamSearchMixin. (#42946)

2026-05-19 07:37:40 +00:00

api_router.py

[Frontend] Cohere chat v2 api support (#47189)

2026-07-31 22:53:54 -07:00

factories.py

[Frontend] Consolidate online serving utils. (#44479)

2026-06-04 06:49:31 +00:00