Hacker News Reader

The write up on the GitHub repo is much more informative than the blog.

When running int8 matmul using onnx performance is ~0.6TF.

Thanks—we changed the URL to that from https://petewarden.com/2024/10/16/ai-pcs-arent-very-good-at-.... Readers may way want to look at both, of course!

Oh, maybe also change the title? I flagged it because of the title/url not matching.