Latest Work
Engineering write-ups and research notes
The 1.2 ms Eigensolver That Never Ran
Bleeding Llama: When AI Model Files Become Memory Leaks
Porting CUDA FFT to Mojo: Achieving Bit-Exact Precision
Optimizing AlphaFold's Triangle Multiplicative Update: A First Look at GPU Performance Engineering
Multi-GPU Programming with AMD's Iris Framework for Triton
Gluon: When Triton Isn't Low-Level Enough
The Hidden Math Bug That Makes AI Unpredictable
Building Agents for Small Language Models: A Deep Dive into Lightweight AI
AMD GPU Support in Triton Gluon Framework
RustBPE: High-Performance BPE Tokenizer Training in Rust