[GH-ISSUE #804] Unable to connect with local llama.cpp #111

New issue

Closed

opened 2026-10-18 14:09:04 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:09:04 +00:00

Owner

Originally created by @chrisrp on GitHub (Nov 9, 2025).
Original GitHub issue: https://github.com/open-webui/docs/issues/804

I have installed llama.cpp on macOS M1 and it's running correctly as I am able to access from http://localhost:8080/.

Following here the instructions I get an error.

This is what I see at the server console:

srv log_server_r: request: GET /v1/api/version 127.0.0.1 404

Here is the server version:

$ llama-server --version                      
version: 5460 (3079e9ac)
built with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0

Originally created by @chrisrp on GitHub (Nov 9, 2025). Original GitHub issue: https://github.com/open-webui/docs/issues/804 I have installed llama.cpp on macOS M1 and it's running correctly as I am able to access from `http://localhost:8080/`. Following here the [instructions](https://docs.openwebui.com/getting-started/quick-start/starting-with-llama-cpp/#step-4-connect-llamacpp-to-open-webui) I get an error. This is what I see at the server console: `srv log_server_r: request: GET /v1/api/version 127.0.0.1 404` Here is the server version: ```bash $ llama-server --version version: 5460 (3079e9ac) built with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0 ```

bsakaguchi closed this issue

2026-10-18 14:09:04 +00:00

bsakaguchi referenced this issue

2026-10-18 14:10:34 +00:00

[PR #111] [MERGED] add continue.dev tutorial for vscode #254