News for hackers. Stuff that matters.

A comment on Tinygrad 0.9.0. Parent comment

Re:Tinygrad 0.9.0 by anthonix1 on Wednesday May 29, 2024 @12:43AM (#40508550)
Seems to be an issue on their side. E.g., for a step of GPT2 training on a 7900 XTX [1]: tinygrad is ~440ms, PyTorch 2.4.0.dev20240513 is ~97ms, Karpathy's llm.c with ROCm is ~79ms, and llm.c with custom kernels is ~58ms

[1] https://github.com/anthonix/llm.c [2] https://github.com/tinygrad/tinygrad/issues/4301

[ Parent | on HN ]
Re:Tinygrad 0.9.0 by xiphias2 on Wednesday May 29, 2024 @11:16AM (#40512842)
That issue seems a month old, while the 58ms number looks 1 day old.

I have seen last month getting a lot of work done in improving performance (it's in the release announcement as well), but of course I still don't think it can compete with that number...still, a new comparision would be cool.

[ Parent | on HN ]
Re:Tinygrad 0.9.0 by anthonix1 on Wednesday May 29, 2024 @11:26AM (#40512994)
Ran tinygrad again about a week ago, no change.

And still no comment on the issue, will re-run if there is any comment.

[ Parent | on HN ]
Re:Tinygrad 0.9.0 by xiphias2 on Wednesday May 29, 2024 @11:41AM (#40513146)
Thanks for the answer
[ Parent | on HN ]