Woosuk Kwon 464dd985e3 Fix num_gpus when TP > 1 (#1852)

2023-12-03 12:24:30 -08:00

..

__init__.py

Change the name to vLLM (#150)

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

arg_utils.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

async_llm_engine.py

Fix num_gpus when TP > 1 (#1852)

2023-12-03 12:24:30 -08:00

llm_engine.py

Fix num_gpus when TP > 1 (#1852)

2023-12-03 12:24:30 -08:00

metrics.py

Add Production Metrics in Prometheus format (#1890)

2023-12-02 16:37:44 -08:00

ray_utils.py

Better integration with Ray Serve (#1821)

2023-11-29 13:25:43 -08:00