hari-hm a909077d22 Return top-p/top-k sampling mask/nucleas (#27408)

2026-07-13 17:58:51 -05:00

..

penaltylib

[Perf] Avoid per-decode-step host sync in min_new_tokens penalty (#28397)

2026-06-15 23:32:28 -07:00

custom_logit_processor.py

Fix Req array token-id concatenation (#26182)

2026-06-06 19:59:51 -07:00

sampling_batch_info.py

Return top-p/top-k sampling mask/nucleas (#27408)

2026-07-13 17:58:51 -05:00

sampling_params.py

Remove legacy Sphinx docs/ and finish the Mintlify cutover (#28964)

2026-07-13 15:06:08 -07:00