microsoft/BitNet
Official inference framework for 1-bit LLMs
Minimalist ML framework for Rust
Official inference framework for 1-bit LLMs
LLM training code for Databricks foundation models
🦖 X—LLM: Cutting Edge & Easy LLM Finetuning
llama.cpp fork with additional SOTA quants and improved performance
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
1 capture since 2026-05-25