lan-inference-endpoint
Public
Forked from
Forked from
Forked from
README.md
A fork of lmstudio/openai-compat-endpoint that lets LM Studio's chat UI talk to an OpenAI-compatible server on your local network (LM Studio, llama.cpp, vLLM, Ollama, etc.) instead of a cloud provider.
model is now a free-text field, not a dropdown of Claude/GPT models. Model IDs are sent exactly as typed.README.md
A fork of lmstudio/openai-compat-endpoint that lets LM Studio's chat UI talk to an OpenAI-compatible server on your local network (LM Studio, llama.cpp, vLLM, Ollama, etc.) instead of a cloud provider.
model is now a free-text field, not a dropdown of Claude/GPT models. Model IDs are sent exactly as typed.In the plugin's global settings, set:
http://192.168.1.123:1234/v1Then type the model ID your server expects in the generator's config.
In the plugin's global settings, set:
http://192.168.1.123:1234/v1Then type the model ID your server expects in the generator's config.