An opiniated Docker image for troubleshooting purposes especially within a Kubernetes cluster

An OpenAI API compatible server for local LLMs - llama2, mistral, codellama

A lightweight LLaMA.cpp HTTP server image based on Alpine.

Image size: ~2.85MiB. Llama GPT, written in go. USER: nobody.

geopython/stetl

geopython

Stetl - Streaming ETL in Python - Docker Images

Latest ollama/ollama image with pre-downloaded llama2 model: https://ollama.ai/library/llama2

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases,

openruntimes/python

openruntimes

Python Serverless Runtime

revolutionsystems/python

revolutionsystems

Optimized Python Images

InferCrate: self-hosted Ollama server. Secure by default, Bearer token auth, OpenAI-compatible API.

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