mostlygeek/llama-swap but runs inside Alpine Linux. Lightweight, secure, and resource friendly

llama.cpp with env exposed config, suitable for RunPod

I have no idea what is going on

This image has been deprecated since the release of OPEA v1.2.

LLaMA C++ with GPT OSS Implementation on GPU Offload

A small, more complete, Python Docker image based on Alpine Linux.

shopify-slate

Model servers based on Ollama with pre-downloaded models, allowing version freeze and quick startup.

RnDnet platform execution container. Use python python:3.7-slim and BFJ.py

llama.cpp for quantizing and inferencing large language models in C++

Soft fork of Ollama with the opencoti engine, per-model settings and dynamic slots. CUDA, amd64

An Ollama Docker Image

Python Image for the TWT Weekly Challenges