AIC★ 1,028⑂ 111 forksMIT
microsoft/Tutel
TUTEL ACCELERATES MOE IN C
Optimized Mixture-of-Experts library for accelerated LLM inference with FP8, NVFP4, and MXFP4 support.
// KEY FEATURES
- FP8, NVFP4, MXFP4 support for low precision
- Compatible with GptOss, DeepSeek, Kimi-K2, Qwen3
- Written in pure C, minimal dependencies
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram