[MoE][int8] add quantization to MoE dropped implementation - Githubissues

AI-Hypercomputer / maxtext

A simple, performant and scalable Jax LLM!

Apache License 2.0

1.47k stars 275 forks source link

[MoE][int8] add quantization to MoE dropped implementation #873

Closed ZhiyuLi-goog closed 2 weeks ago