Shuolei Wangandaoshen02 b89852aad0 [RL][Frontend] Return token-level weight-version spans on final outputs (#59582) ...

Signed-off-by: Shuolei Wang <shuoleiwang123@gmail.com>
Signed-off-by: Shuolei Wang <948904026@qq.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>

2026-10-11 11:33:29 +08:00

..

weight_transfer

[Feature] Add native ModelExpress weight transfer backend (#58399)

2026-10-02 02:29:35 +00:00

async_rl.md

[RL][Frontend] Return token-level weight-version spans on final outputs (#59582)

2026-10-11 11:33:29 +08:00

layerwise.md

Weight sync refactor + move sparse nccl engine (#44353)

2026-07-01 01:25:19 -07:00

prompt_token_id_logprobs.md

[Feature] Per-row candidate IDs for prefill token scoring (M2 of #56860) (#56984)

2026-10-03 14:17:09 +00:00

rlhf.md

support rl feature : weight checker (#51350)

2026-09-30 03:13:43 +00:00

sampling_mask.md

[Bugfix] Preserve sampling masks in DELTA and TITO streaming outputs (#55935)

2026-10-01 14:43:38 +08:00

trl.md

Updated TRL integration docs (#25684)

2025-09-30 03:10:55 -07:00

weight_checker.md

support rl feature : weight checker (#51350)

2026-09-30 03:13:43 +00:00