Fp8 runs ~100 tflops faster when the kernel name has "cutlass" in it

Re:Fp8 runs ~100 tflops faster when the kernel name has "cut... by amelius on Friday October 03, 2025 @05:02AM (#45460699)

Can't git-bisect simply ignore commits with a commit message smaller than N characters?

[ Parent | on HN ]

Re:Fp8 runs ~100 tflops faster when the kernel name has "cut... by lambdaone on Friday October 03, 2025 @05:18AM (#45460810)

That might sound facile, but it's actually a great idea. Being able to ignore commits based on regexes would be even more powerful.

[ Parent | on HN ]

Re:Fp8 runs ~100 tflops faster when the kernel name has "cut... by s_gourichon on Friday October 03, 2025 @05:53AM (#45461051)

Not sure it really has huge benefits, but I guess something like this should work:

``` #!/bin/sh N=20 msg_len=$(git log -1 --pretty=%B | wc -c) if [ "$msg_len" -lt "$N" ]; then exit 125 fi # Here you would run your actual test and report 0 (good), 1 (bad) as needed exit 0 ```

[ Parent | on HN ]

Re:Fp8 runs ~100 tflops faster when the kernel name has "cut... by lmm on Friday October 03, 2025 @03:42PM (#45466967)

Yes - or, being more principled, you can tell it to only use mainline commits (first parent) if landing on a whole PR is what you want.

[ Parent | on HN ]