yugong333 ffe1fc7a28 Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005) ...

Signed-off-by: Yu Gong <yu3.gong@gmail.com>

2026-02-02 12:30:06 -05:00

..

__init__.py

Change the name to vLLM (#150)

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

arg_utils.py

Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)

2026-02-02 12:30:06 -05:00

async_llm_engine.py

[V0 Deprecation] Remove AsyncLLMEngine (#25025)

2025-09-18 11:07:42 -07:00

llm_engine.py

[V0 Deprecation] Remove LLMEngine (#25033)

2025-09-20 17:56:30 -07:00

protocol.py

[Refactor] Make Renderer an abstract class (#33479)

2026-02-01 10:36:30 +08:00