Deep-dive worklog: optimizing CUDA GEMM from naive kernel to shared-memory tiling

abhijithneil · x · 2026-09-22

Independent researcher Anshuman Mishra published part 4 of his 'How to make your models fast' series: a detailed worklog on making CUDA GEMM fast, with open-sourced code.

Key flow:

Each step follows a quantify-implement-verify loop, making it a practical hands-on guide into inference engineering and CUDA kernel optimization.

Original post →

More from Infra

Infra channel →