On Sun, May 17, 2026 at 08:56:06PM +0200, Mauro Carvalho Chehab wrote: > By "reproduce locally", I didn't mean in strict sense. Sure, LLM answers > won't be identical, but I suspect that at least most of the major issues > on a patch series would be reported by any decent model. > > So, if we have something that one can locally run using its GPU, being > able to get an answer in the range of a couple of minutes per patch > should be enough to catch most of the issues.
That should be possible now, you can submit a patch locally to the system. I have a "cheat-sheet" around here somewhere that explains how to do that, no idea why it's not part of the documentation. I can dig it up after breakfast... greg k-h
