← 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 GLM/Kimi/Gpt/DeepSeek/Qwen using FP8/NVFP4/MXFP4

79.1/100
★ 1.0KForks: 111
View on GitHub →
Loading report...

Similar Projects

kimi-k3-in-c

85

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

C★ 8.9K

llama.rn

78

React Native binding of llama.cpp

C★ 1.0K

hax

78

A minimalist, terminal-native coding agent written in C.

C★ 875

microgpt-c

56

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

C★ 845
← Back to List