[None][feat] Support rejection sampling under attention DP (incl. LM-head TP)#16544

zhaoyangwang-nvidia merged 5 commits into

NVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom

zhaoyangwang-nvidia:support-adp-lm-head-tp-advanced-samplingzhaoyangwang-nvidia/TensorRT-LLM:support-adp-lm-head-tp-advanced-samplingCopy head branch name to clipboard