Skip to content

[TRTLLM-13321][feat] Extend rejection sampling to one-model speculative decoding (MTP/DRAFT_TARGET/PARD/DFLASH)#15775

Merged
zhaoyangwang-nvidia merged 8 commits into
NVIDIA:mainfrom
zhaoyangwang-nvidia:rejection-one-model-spec
Jul 16, 2026
Merged

[TRTLLM-13321][feat] Extend rejection sampling to one-model speculative decoding (MTP/DRAFT_TARGET/PARD/DFLASH)#15775
zhaoyangwang-nvidia merged 8 commits into
NVIDIA:mainfrom
zhaoyangwang-nvidia:rejection-one-model-spec

Commits

Commits on Jul 15, 2026

Commits on Jul 16, 2026