Sabre Shao

Sabre Shao#

Sabre Shao is a senior manager of the FDE China team, specializing in LLM inference and performance optimization on AMD Instinct accelerators, including GPU kernel optimization, GPU architecture, distributed inference, and production deployment.

Posts by Sabre Shao

https://rocm.blogs.amd.com/artificial-intelligence/glm5.2-mi355x-kvcache/README.html