This is why I like modern Renaults/Dacias. They all come with a single button to turn all of this stuff off, or to a preset of your choosing. No need to fiddle with a screen, nothing you cannot disable. Bliss.
The url to connect to ollama seems to just be hard coded so I don't see why you couldn't point this at a different machine on your network rather than having Ollama running locally on every machine you need this for like the readme implies.
I agree. AMD should just go all in on vulkan I think, The ROCm compatibility list is terrible compared to...every modern device and probably some ancient gpus that can be made to work with vulkan as well.
Considering they created mantle, you would think it would be the obvious move too.
No experimental flag option, no "you can use the fork that works fine but we don't have capacity to support this" just a hard "no, we think it's unreliable". I guess they just want you to drop them and use llama.cpp.
Not quite what you're after but if you want a fanless option that runs full linux and doesn't use much battery, the new argon 40 CM5 laptop that's being built looks like it could be viable as long as you'd be happy with that much of a drop in performance and a few pi based niggles (No USB C video, only one pcie lane for the SSD, etc.)
I agree. I have been using it as a drop in docker replacement alongside podman compose via aliases for years now and I often just forget I am not using docker. The only time it bit me recently is when some scripts were looking for containers with docker specific labels and I had to figure out why they failed only for me.
True, but the fact a pi can even compete on paper in some areas with a modern intel chip is pretty impressive. 3x isn't the power difference for all workloads but probably is for common ones like transcode etc.
I think we often forget just how far the pi has come from the armhf days.