vllm/vllm/engine/multiprocessing
2024-10-14 15:05:52 -07:00
..
__init__.py [Core] [Frontend] Priority scheduling for embeddings and in the OpenAI-API (#8965) 2024-10-01 09:58:06 +00:00
client.py [Frontend] merge beam search implementations (#9296) 2024-10-14 15:05:52 -07:00
engine.py [Bugfix] Fix priority in multiprocessing engine (#9277) 2024-10-11 15:35:35 +00:00