[PR #2] [MERGED] Docker Deployment #2

New Issue

2026-02-15T20:17:02-05:00

yindo commented

2026-02-15 20:17:02 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/llama-cpp-runner/pull/2
Author: @pkeffect
Created: 4/18/2025
Status: ✅ Merged
Merged: 4/18/2025
Merged by: @tjbck

Base: main ← Head: main

📝 Commits (2)

f7ecd27 New Deployment
fd8f43a refactor and update

📊 Changes

5 files changed (+237 additions, -3 deletions)

View changed files

📝 .gitignore (+4 -3)
➕ Dockerfile (+117 -0)
📝 README.md (+14 -0)
➕ compose.yaml (+23 -0)
➕ proxy_server.py (+79 -0)

📄 Description

Adds a few files needed to wrap this up and run properly in Docker
Tested on Windows 11, WSL2 Ubuntu 24.20
compose.yaml uses locally mounted directories (remove . from them to switch to default Docker Volumes)

Dockerfile
compose.yaml
proxy_server.py

Changelog

v0.0.2 (April 18, 2025)
Optimized Dockerfile for smaller image size
Created proper .gitignore for model and cache directories
Fixed proxy server script issues
Added health check to Docker compose

v0.0.1 (Initial Release)
Basic llama.cpp integration
Automatic binary downloads
HTTP server on port 3636
Model caching system
Timeout handling for idle servers

To Do

GPU inference support

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/llama-cpp-runner/pull/2 **Author:** [@pkeffect](https://github.com/pkeffect) **Created:** 4/18/2025 **Status:** ✅ Merged **Merged:** 4/18/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (2) - [`f7ecd27`](https://github.com/open-webui/llama-cpp-runner/commit/f7ecd272b2db2b3f7b40d97f694976a0464de059) New Deployment - [`fd8f43a`](https://github.com/open-webui/llama-cpp-runner/commit/fd8f43a156a6b9fbf50d7128c1d58a0d16e152f0) refactor and update ### 📊 Changes **5 files changed** (+237 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `.gitignore` (+4 -3) ➕ `Dockerfile` (+117 -0) 📝 `README.md` (+14 -0) ➕ `compose.yaml` (+23 -0) ➕ `proxy_server.py` (+79 -0) </details> ### 📄 Description Adds a few files needed to wrap this up and run properly in Docker Tested on Windows 11, WSL2 Ubuntu 24.20 compose.yaml uses locally mounted directories (remove . from them to switch to default Docker Volumes) - Dockerfile - compose.yaml - proxy_server.py ### Changelog v0.0.2 (April 18, 2025) Optimized Dockerfile for smaller image size Created proper .gitignore for model and cache directories Fixed proxy server script issues Added health check to Docker compose v0.0.1 (Initial Release) Basic llama.cpp integration Automatic binary downloads HTTP server on port 3636 Model caching system Timeout handling for idle servers ### To Do GPU inference support --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

yindo added the pull-request label 2026-02-15 20:17:02 -05:00

yindo closed this issue

2026-02-15 20:17:02 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: open-webui/llama-cpp-runner#2