Xiaochun Tong

Intern of Technical Staff, Foundations

Xiaochun Tong is an Intern of Technical Staff in the Foundations team at Cohere. He is also a PhD candidate from the University of Waterloo. His work at Cohere focuses on developing high performance GPU kernels to accelerate LLM inference.

An abstract purple image, with organic graphic design.

AI for Developers Research

Inside the megakernel serving engine for North Mini Code

Xiaochun Tong