R_REDDYX.XYZ
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
#deepseek#llm#mixture-of-experts#moe#pytorch
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

TRADEMEMORY PROTOCOL: AI TRADING★ 1028Uniting CloudBase and AI★ 1029EASY-AGENT: AI CODING AGENT IN TERMINAL★ 1029ОБЗОР MULTIMODAL CHAIN-OF-THOUGHT★ 1029ClawGod Patch for Claude★ 1026Distributed LLM for All★ 1030

← FULL CATALOG

microsoft/Tutel — Tutel Accelerates Moe IN C | REDDYX AI