Files

Shengqi Chen 75e01a39a1 [Feature] NUMA binding support for GPU workers (#38635 )

Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Jason Li <jasonlizhengjian@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

2026-04-08 09:55:24 -07:00

conserving_memory.md

2026-03-12 07:57:47 -07:00

engine_args.md

2025-12-26 12:47:41 +00:00

env_vars.md

2025-11-19 03:32:04 -08:00

model_resolution.md

2025-07-21 12:18:33 +01:00

optimization.md

2026-04-08 09:55:24 -07:00

README.md

2025-10-17 02:22:06 -07:00

serve_args.md

2025-11-15 05:33:27 -08:00

Configuration Options

This section lists the most common options for running vLLM.

There are three main levels of configuration, from highest priority to lowest priority: