News for hackers. Stuff that matters.

A comment on FP8 is ~100 tflops faster when the kernel name has "cutlass" in it. Parent comment

Re:FP8 is ~100 tflops faster when the kernel name has "cutla... by btbuilder on Friday July 11, 2025 @11:35AM (#44533366)
I believe the driver silently swapped the textures to lower quality ones that looked worse but gave a performance boost.
[ Parent | on HN ]

There are no comments on this comment yet.