yhyang201 c377923304 [feat] Reduce GPU memory overhead by using weakref (#9673)

2025-08-28 01:09:06 -07:00

..

__init__.py

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

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

frequency_penalty.py

[EAGLE] many fixes for eagle (#4195)

2025-03-07 22:12:13 -08:00

min_new_tokens.py

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

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

orchestrator.py

[feat] Reduce GPU memory overhead by using weakref (#9673)

2025-08-28 01:09:06 -07:00

presence_penalty.py

[EAGLE] many fixes for eagle (#4195)

2025-03-07 22:12:13 -08:00