History

hailin 38d813617c first commit		2025-08-03 20:28:19 +08:00
..
README.md	first commit	2025-08-03 20:28:19 +08:00
conserving_memory.md	first commit	2025-08-03 20:28:19 +08:00
engine_args.md	first commit	2025-08-03 20:28:19 +08:00
env_vars.md	first commit	2025-08-03 20:28:19 +08:00
model_resolution.md	first commit	2025-08-03 20:28:19 +08:00
optimization.md	first commit	2025-08-03 20:28:19 +08:00
serve_args.md	first commit	2025-08-03 20:28:19 +08:00

README.md

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:

[Request parameters][completions-api] and [input arguments][sampling-params]
Engine arguments
Environment variables