Repository navigation
Replies: 3 comments
|
You can run llama.cpp on your machine and then set the Codex configuration file to use a local LLM. You can install #21174 which also shows how to set up the configuration. |
0 replies
|
Yes. llama-server supports the Responses API, so add a provider to model_provider = "llamacpp"
model = "<your --alias>"
[model_providers.llamacpp]
name = "llama.cpp"
base_url = "http://localhost:8080/v1"
wire_api = "responses"You could also try https://github.com/llmmanorg/llmman (I maintain it), which sets this up for you: |
0 replies
This is a HTTP unified local gateway which allows to have all local and cloud models available in codex. https://github.com/sr3m/llama-codex The script gives you the step-by-step and makes all the changes for you. Everything is automated, you can try it. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Can llama.cpp be integrated into the Codex app for use?
All reactions