Jie Fu (傅杰) a4e2b26856 [Bugfix] Significant performance drop on CPUs with --num-scheduler-steps > 1 (#11794)

2025-01-07 16:15:50 -08:00

..

multiprocessing

[Doc] Update docs to refer to pooling models (#11093)

2024-12-11 13:36:27 +00:00

output_processor

[Doc][2/N] Reorganize Models and Usage sections (#11755)

2025-01-06 21:40:31 +08:00

__init__.py

Change the name to vLLM (#150)

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

arg_utils.py

[Bugfix] Significant performance drop on CPUs with --num-scheduler-steps > 1 (#11794)

2025-01-07 16:15:50 -08:00

async_llm_engine.py

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

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

async_timeout.py

[Bugfix] AsyncLLMEngine hangs with asyncio.run (#5654)

2024-06-19 13:57:12 -07:00

llm_engine.py

[Bugfix] Last token measurement fix (#11376)

2024-12-28 11:34:46 +08:00

metrics_types.py

monitor metrics of tokens per step using cudagraph batchsizes (#11031)

2024-12-09 22:35:36 -08:00

metrics.py

monitor metrics of tokens per step using cudagraph batchsizes (#11031)

2024-12-09 22:35:36 -08:00

protocol.py

[Doc] Update docs to refer to pooling models (#11093)

2024-12-11 13:36:27 +00:00