Writing

March 2026

GTC 2026: Achieve Peak Tensor Core Performance for GEMM on Blackwell via CUTLASS Python

April 28, 2021

CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment

August 26, 2019

Anatomy of a High-Speed Convolution

June 24, 2018

Making Neural Nets Work With Low Precision