Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

Browse Source

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>

...

This commit is contained in:

Lianmin Zheng

2025-03-03 00:12:04 -08:00

co-authored by SangBin Cho dhou-xai Hanming Lu

parent 0194948fd9

commit ac2387279e

86 changed files with 4116 additions and 2015 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

python/sglang/srt/managers/scheduler.py

+611 -173

File diff suppressed because it is too large Load Diff