ulmentflam/llm.mojo

GPT-2 training in pure Mojo with hand-written CUDA and Metal GPU kernels. llm.c parity in bf16 on NVIDIA, 1.72x faster than PyTorch MPS on Apple Silicon.

1 best points · 0 comments · 1 Hacker News post · 30 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Llm.c ported to Mojo with Metal kernels, 1.72x faster than PyTorch MPs (1 points, 0 comments, by ulmentflam, 2026-07-14)