Nick HillandAntoni Baum 2efce05dc3 [Fix] Avoid pickling entire LLMEngine for Ray workers (#3207) ...

Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

2024-03-06 00:17:20 +00:00

..

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

arg_utils.py

Push logprob generation to LLMEngine (#3065)

2024-03-04 19:54:06 +00:00

async_llm_engine.py

Add health check, make async Engine more robust (#3015)

2024-03-04 22:01:40 +00:00

llm_engine.py

[Fix] Avoid pickling entire LLMEngine for Ray workers (#3207)

2024-03-06 00:17:20 +00:00

metrics.py

allow user chose log level by --log-level instead of fixed 'info'. (#3109)

2024-03-01 23:28:41 +00:00

ray_utils.py

[Ray] Integration compiled DAG off by default (#2471)

2024-02-08 09:57:25 -08:00