Cyrus Leung 051eaf6db3 [Model] Add user-configurable task for models that support both generation and embedding (#9424)

2024-10-18 11:31:58 -07:00

..

block

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

__init__.py

Change the name to vLLM (#150)

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

block_manager.py

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

evictor_v1.py

[Bugfix] Remove deprecated @abstractproperty (#5174)

2024-06-01 22:40:25 +00:00

evictor_v2.py

[MISC] Add prefix cache hit rate to metrics (#7606)

2024-08-19 11:52:07 -07:00

interfaces.py

[Core] Deprecating block manager v1 and make block manager v2 default (#8704)

2024-10-17 11:38:15 -05:00

placeholder_block_space_manager.py

[Model] Support Mamba (#6484)

2024-10-11 15:40:06 +00:00

scheduler.py

[Model] Add user-configurable task for models that support both generation and embedding (#9424)

2024-10-18 11:31:58 -07:00