Does this require an Oriveo server proxy?
No. Native apps connect directly. The web app uses browser Local Network Access and CORS and does not proxy a private address through Oriveo servers.
vLLM on multiple devices: a direct local compute client
Connect multiple devices to vLLM running on your own computer. Configure the listener, firewall, private network, and Oriveo without exposing the engine to the public internet.
- Use the compute you already own from another device, with no API credential on local HTTP.
- Oriveo is a client: vLLM must run on a computer. It does not run the model on your phone.
- Never expose an unauthenticated engine to the public internet. Use local Wi-Fi or a supported private VPN such as Tailscale; public and mixed DNS targets are rejected.
Prepare vLLM
Start the engine on a private interface, confirm the port locally, then allow that port only on your LAN or private VPN.
- vllm serve MODEL --host 0.0.0.0 --port 8000
- GET http://127.0.0.1:8000/v1/models
- TCP 8000 · LAN / private VPN
Connect from multiple devices
Choose Local compute in Providers, select the matching engine, enter the private address, and verify the discovered model before saving.
Keep the endpoint private
Never expose an unauthenticated engine to the public internet. Use local Wi-Fi or a supported private VPN such as Tailscale; public and mixed DNS targets are rejected.
Common app questions
Does the model run on the phone?
No. The model runs on your computer or server; the phone is the client.
Keep the endpoint private?
vllm serve MODEL --host 0.0.0.0 --port 8000 · GET http://127.0.0.1:8000/v1/models · TCP 8000 · LAN / private VPN
Connect your own compute
Get the native Oriveo app or desktop download and connect the engine on your private network.
No API key yet? Oriveo Free lets you start without one.
Guides
Local LLM · away from home
Local LLM on away from home: a direct local compute client
Connect away from home to Local LLM running on your own computer. Configure the listener, firewall, private network, and Oriveo without exposing the engine to the public internet.
llama.cpp · iPhonellama.cpp on iPhone: a direct local compute client
Connect iPhone to llama.cpp running on your own computer. Configure the listener, firewall, private network, and Oriveo without exposing the engine to the public internet.
LM Studio · mobileLM Studio on mobile: a direct local compute client
Connect mobile to LM Studio running on your own computer. Configure the listener, firewall, private network, and Oriveo without exposing the engine to the public internet.