Gilfeather/furnace

Open Source Brain Platform | AI training and inference in Rust

Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.

A Rust-native LLM serving engine. One binary, no Python runtime.

Fast, flexible LLM inference

Pure Rust Inference Engine

a fast cross platform AI inference engine 🤖 using Rust 🦀 and WebGPU 🎮

Instant, controllable, local pre-trained AI models in Rust

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

Native Rust inference server for open models on NVIDIA and Apple Silicon. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors + MLX, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio