vllm serve meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0

Category: AI/ML Tooling

vllm serve meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0

Expose the API on all interfaces

Binds the vLLM server to every network interface so other machines on the network can reach the OpenAI-compatible API. Anyone who can connect can use the model, so add --api-key or a firewall rule in untrusted networks. Default is localhost only.
Looking for more? Search all 7,657 commands — works offline, in English or Spanish, and fixes typos.