Nick Hill aea94362c9

[Frontend][V1] Online serving performance improvements (#12287)

2025-01-22 22:22:12 +00:00

..

attention

[Misc] Pass attention to impl backend (#12218)

2025-01-20 23:25:28 +08:00

core

[Core] Support reset_prefix_cache (#12284)

2025-01-22 18:52:27 +00:00

engine

[Frontend][V1] Online serving performance improvements (#12287)

2025-01-22 22:22:12 +00:00

executor

[Core] Interface for accessing model from VllmRunner (#10353)

2025-01-20 15:00:59 +08:00

metrics

[V1] [2/n] Logging and Metrics - OutputProcessor Abstraction (#11973)

2025-01-13 04:54:10 +00:00

sample

[Doc] Fix typo (#11666)

2025-01-01 08:10:10 +00:00

stats

[ci/lint] Add back default arg for pre-commit (#12279)

2025-01-22 01:15:27 +00:00

worker

[Core] Support fully transparent sleep mode (#11743)

2025-01-22 14:39:32 +08:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

kv_cache_interface.py

[V1] Move more control of kv cache initialization from model_executor to EngineCore (#11960)

2025-01-17 07:39:35 +00:00

outputs.py

[V1] Multiprocessing Tensor Parallel Support for v1 (#9856)

2024-12-10 06:28:14 +00:00

request.py

[Frontend][V1] Online serving performance improvements (#12287)

2025-01-22 22:22:12 +00:00

serial_utils.py

[V1] Use pickle for serializing EngineCoreRequest & Add multimodal inputs to EngineCoreRequest (#10245)

2024-11-12 08:57:14 -08:00

utils.py

[V1] Move more control of kv cache initialization from model_executor to EngineCore (#11960)

2025-01-17 07:39:35 +00:00