Old Man
Old Man
> @oldmanjk This issue is about MacOS I'm aware. That's why I mentioned my comment was on Linux. Sometimes issues are cross-platform
> @oldmanjk I would recommend creating a new issue for Linux, as @easp said, these comments are around MacOS. There are already several issues around this. I recommend you guys...
> We've changed to a subprocess model in the past few versions which likely resolves this when the model unloads. Are people still seeing a large footprint when idle on...
I have a rig with three graphics cards that I would like to run three separate models on simultaneously and have them group chat
That's what I'm currently doing (loosely), but you also have to map each instance to a specific GPU. It works, but it's very clunky to setup. A GUI would be...
> run in docker, stick containers separately with gpu1,gpu2 or cpu only, open-webui can work with multiply ollama instances > > ``` > version: '3.8' > > services: > ollama:...
Can we have control over which model is run on which GPU?
You might want to wait. I think I'm still dragging more changes out of the huggingface/meta guys. So frustrating
I wish I knew. What's clear to me is they haven't given this proper attention yet and I'd caution everyone to slow down. Please spread the word. I deleted my...
A GUI would be even nicer