Rui Qiao 9832e5572a

[V1] Unify VLLM_ENABLE_V1_MULTIPROCESSING handling in RayExecutor (#11472)

2024-12-24 19:49:46 -08:00

..

__init__.py

Enable mypy checking on V1 code (#11105)

2024-12-14 09:54:04 -08:00

async_llm.py

[V1] Make AsyncLLMEngine v1-v0 opaque (#11383)

2024-12-21 15:14:08 +08:00

async_stream.py

[Misc] Rename embedding classes to pooling (#10801)

2024-12-01 14:36:51 +08:00

core_client.py

[V1][Core] Use weakref.finalize instead of atexit (#11242)

2024-12-16 22:11:33 -08:00

core.py

[V1] Prefix caching for vision language models (#11187)

2024-12-17 16:37:59 -08:00

detokenizer.py

Enable mypy checking on V1 code (#11105)

2024-12-14 09:54:04 -08:00

llm_engine.py

[V1] Unify VLLM_ENABLE_V1_MULTIPROCESSING handling in RayExecutor (#11472)

2024-12-24 19:49:46 -08:00

mm_input_mapper.py

[V1][Bugfix] Skip hashing empty or None mm_data (#11386)

2024-12-21 14:22:21 +09:00

processor.py

[V1] Fix multimodal profiling for Molmo (#11325)

2024-12-19 16:27:22 +00:00