vllm
Serve large language models efficiently and interact with them through an OpenAI-compatible API. tldr-pages
On several platforms
Several platforms
Launch an OpenAI-compatible API server for a model
vllm serve model_nameIdentifyServe a model on a specific host and port
vllm serve model_name --host 0.0.0.0 --port 8000IdentifyStart an interactive chat session
vllm chatIdentifyRun batch prompts from a file and write results to a file
vllm run-batch -i input.jsonl -o output.jsonl --model model_nameIdentifyPrint environment information for bug reports
vllm collect-envIdentifyList all available subcommands
vllm --helpIdentify