vllm-chat
Generate chat completions via the running API server using the OpenAI-compatible REST API. tldr-pages
On several platforms
Several platforms
Send a single chat prompt to the API server and get a response
vllm chat --quick "message"IdentifyChat with a specific model name
vllm chat --model-name model_name --quick "message"IdentifyChat with a custom system prompt
vllm chat --system-prompt "system_prompt" --quick "message"IdentifyChat using a custom API server URL
vllm chat --url http://custom-host:port/v1 --quick "message"IdentifyChat with an API key for authentication
vllm chat --api-key your_api_key --quick "message"IdentifyStart an interactive chat session
vllm chatIdentify