New comment by AndReics in "Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch"

AndReics — Mon, 29 Jun 2026 13:30:59 +0000

i see really cool, where i failed was trying to build my own matrix operations library, it was just too much, but using cuBLAS definitely helps, i'll look into the custom kernels you wrote they seem interesting!

did you build the backprop yourself? it is a really cool project to build and i think you can agree that it teaches you a lot of how LLMS and machine learning in general works.

New comment by AndReics in "Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch"

AndReics — Mon, 29 Jun 2026 10:56:49 +0000

Wow that's really cool i'll definitely check it out! have played around with machine learning algorithms built from scratch in c / cuda too, but once i hit the cuda part of it i kinda just left it to the side. i'm curious how did you use CUDA to optimize the matrix multiplications? how optimized is training, does it take much longer then using pytorch?

Hacker News: AndReics

New comment by AndReics in "Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch"

New comment by AndReics in "Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch"