Comment by buyucu
6 months ago
This is incorrect. The effort it took to enable Vulkan was relatively minor. The PR is short and to be honest it doesn't do much, because it doesn't need to.
6 months ago
This is incorrect. The effort it took to enable Vulkan was relatively minor. The PR is short and to be honest it doesn't do much, because it doesn't need to.
that PR doesn't actually work though -- it finds the Vulkan libraries and has some memory accounting logic, but the bits to actually build a Vulkan llama.cpp runner are not there. I'm not sure why its author deems it ready for inclusion.
(I mean, the missing work should not be much, but it still has to be done)
the pr was working 6 months ago and it has been rebased multiple times as the ollama team kept ignoring it and mainline moved. I'm using it right now.
This is a change from your response to the comment that I linked to, where you said it was a good point. Why the difference?
Maybe I should clarify that I'm not saying that the effort to enable a new backend is substantial, I'm saying that my understanding of that comment (the one you acknowledged made a good argument) is that the maintenance burden of having a new backend is substantial.
I didn't say it was a good point. I said I disagree, but it's a respectable opinion I could imagine someone having.
Okay, now we're playing semantics. "Reasonable argument" were your words. What changed between then and now to where the same argument is now "incorrect"?
3 replies →