← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Cmicrosoft/Tutel

Tutel

Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4

77.6/100
★ 992Forks: 109
View on GitHub →
Loading report...

Similar Projects

picolm

51

Run a 1-billion parameter LLM on a $10 board with 256MB RAM

C★ 1.6K

esp-ai

67

The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧~

C★ 834

nanolang

74

A tiny experimental language designed to be targeted by coding LLMs

C★ 601

microgpt-c

56

The most atomic way to train and inference a GPT in pure, dependency-free C

C★ 571
← Back to List