News for hackers. Stuff that matters.

A comment on Show HN: Flash Attention in ~100 lines of CUDA. Parent comment

Re:Show HN: Flash Attention in ~100 lines of CUDA by synquid on Sunday March 17, 2024 @05:11AM (#39733002)
Triton has an AMD backend, although work is still ongoing.
[ Parent | on HN ]
Re:Show HN: Flash Attention in ~100 lines of CUDA by imtringued on Sunday March 17, 2024 @08:26AM (#39733986)
You will also be able to use Triton to target Ryzen AI.
[ Parent | on HN ]