Lianmin Zheng ac2387279e 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>

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

..

__init__.py

Model: Support Qwen 2.5 vl (#3258)

2025-02-16 00:58:53 -08:00

chatglm.py

Remove vllm dependency in model config (#2809)

2025-01-09 17:51:56 +08:00

dbrx.py

Remove vllm dependency in model config (#2809)

2025-01-09 17:51:56 +08:00

device_config.py

Enable CPU device on SGLang (#2806)

2025-01-16 21:22:53 -08:00

exaone.py

EXAONE 3.0 Model Support (#1258)

2024-08-30 08:08:28 +00:00

load_config.py

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

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

model_config.py

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

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

qwen2_5_vl_config.py

fix: remove dependency on latest transformers impl (#3635)

2025-02-19 01:14:11 +08:00