- 28 Apr, 2025 1 commit
-
-
Lianmin Zheng authored
-
- 03 Mar, 2025 1 commit
-
-
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>
-