-
Lianmin Zheng authored
Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988) Co-authored-by:
SangBin Cho <rkooo567@gmail.com> Co-authored-by:
dhou-xai <dhou@x.ai> Co-authored-by:
Hanming Lu <hanming_lu@berkeley.edu>
ac238727