“distributed-computing”

ColossalAI

Making large AI models cheaper, faster and more accessible

Daft

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

distributed-llama

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

beta9

Ultrafast serverless GPU inference, sandboxes, and background jobs

taOS

Self-hosted AI agent OS with memory, chat, and multi-framework group chat support.