Eric Curtin
Eric Curtin
> Sorry everyone for the lack of activity. Perfect storm of job change and life events (all good!). Will try and push this (and related PRs) through in the next...
> The macOS situation is a bit easier to handle because there is only the Metal backend, and we know that it is available on every device. For windows and...
If winget does indeed use just Vulkan for now, it's a good start
> > > For Windows arm64 I suggest to use only the CPU backend. > > > > > > Would there be any advantage of also bundling the OpenCL...
I was wondering this too
Would be a great feature
ramalama essentially has it's own toolbox implementation. ramalama by default executes podman internally just like toolbox does. Now one could create a ramalama toolbox if they were hell-bent on doing...
Where toolbox is inconvenient right now is GPU access/AI API enablement whatever we want to call it... We should make contributions to toolbox to make that better though... https://github.com/search?q=repo%3Acontainers%2Ftoolbox+%2Fdev%2Fkfd&type=code "/dev/kfd"...
Well noticed "rag" and "run" prompts are different @bmahabirbu has got this on his radar... @bmahabirbu is well equipped to comment on a lot of these queries
I think the best fix is to implement ramalama login in python3 from scratch it shouldn't be too bad, I've seen at least 3 implementations of it.