Daniel Hiltgen
Daniel Hiltgen
> there's a minor(?) glitch with the amdgpu kernel module That's "working as designed" - the lack of the version file implies this is an upstream amdgpu driver merged into...
The [0.1.33](https://github.com/ollama/ollama/releases) release is available now as a pre-release.
@QIN2DIM please make sure /path/to/models is owned by user `ollama` (or at least writable by that user/group) if you want to continue to run it as a system service.
To clarify some of the error messages, our current build uses the v5 ROCm image base, so the actual error was ``` time=2024-02-24T00:19:40.892Z level=WARN source=llm.go:162 msg="Failed to load dynamic library...
If you're still having problems, please upgrade to the latest release and share your server log so we can see more details. https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md
We're tracking custom installation for windows in #2776
Can you share what driver version you have on the host? `nvidia-smi` on the host should report it.
Hmm... I have a very similar test setup and haven't been able to reproduce yet. (Ubuntu 22.04 kernel 5.15.0-105-generic) ``` % nvidia-smi Mon Apr 22 23:00:49 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI...
I wonder if this might be a dup of #1500 and the bundled cudart library we bake into the image doesn't support MIG?
I've been working on a [change](https://github.com/ollama/ollama/pull/4067) to how we do GPU discovery that might resolve this issue. I've pushed test images up to Docker Hub for folks to try out....