Scale beam search: multi-LLM, samples-per-prompt, multi-GPU, PTX dedup, NCU caching#139
Open
jiannanWang wants to merge 2 commits into
Open
Scale beam search: multi-LLM, samples-per-prompt, multi-GPU, PTX dedup, NCU caching#139jiannanWang wants to merge 2 commits into
jiannanWang wants to merge 2 commits into