timmyd

Recent Submissions

1. 1. ▲ The Five Eras of KVCache (modular.com) 2 points · 2 months ago · 0 comments
2. 2. ▲ How to Beat Unsloth's CUDA Kernel Using Mojo–With Zero GPU Experience (modular.com) 3 points · 2 months ago · 1 comment
3. 3. ▲ Matrix Multiplication on Nvidia's Blackwell: Part 1 – Introduction (modular.com) 4 points · 7 months ago · 0 comments
4. 4. ▲ Inworld TTS: 20x cheaper, state-of-the-art, text-to-speech (inworld.ai) 27 points · 9 months ago · 1 comment
5. 5. ▲ GPU Comic: When GPU programming hurts so much, all we can do is laugh (comic.modular.com) 15 points · 9 months ago · 3 comments
6. 6. ▲ Scale or Surrender: When watts determine freedom (timdavis.com) 2 points · 10 months ago · 0 comments
7. 7. ▲ Highly efficient matrix transpose in Mojo (veitner.bearblog.dev) 125 points · 10 months ago · 64 comments
8. 8. ▲ Fast vector sum without CUDA (veitner.bearblog.dev) 2 points · 10 months ago · 0 comments
9. 9. ▲ Modular Platform 25.3: 450K+ Lines of Open Source Code and Pip Packaging (modular.com) 1 point · 11 months ago · 0 comments
10. 10. ▲ The Case for a Next-Generation AI Developer Platform (modular.com) 1 point · 3 years ago · 0 comments