You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
i'm currently playing around with the ollama addon and running gemma2:9b on my home assistant computer. So far it works without any problems. The only thing I would like to optimize is the inferrence time. The execution runs on the CPU. Currently the inferrence time is between 5 and 20 seconds, depending on the size of the response. I use this llm to get detailed answers, e.g. “What do you know about the moon”.
Even the gemma2:27b llm runs, but then the output takes even longer.
Running the ollama addon will give some hints:
time=2024-10-02T08:34:23.714Z level=INFO source=gpu.go:199 msg="looking for compatible GPUs"
time=2024-10-02T08:34:23.718Z level=WARN source=amd_linux.go:60 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-10-02T08:34:23.718Z level=INFO source=amd_linux.go:361 msg="no compatible amdgpu devices detected"
time=2024-10-02T08:34:23.718Z level=ERROR source=amd_linux.go:364 msg="amdgpu devices detected but permission problems block access" error="kfd driver not loaded".
Are there any plans to implement these drivers? One of the next kernels should also support NPUs. Are there any plans for Home Assistant?
Describe the issue you are experiencing
Hi,
i'm currently playing around with the ollama addon and running gemma2:9b on my home assistant computer. So far it works without any problems. The only thing I would like to optimize is the inferrence time. The execution runs on the CPU. Currently the inferrence time is between 5 and 20 seconds, depending on the size of the response. I use this llm to get detailed answers, e.g. “What do you know about the moon”.
Even the gemma2:27b llm runs, but then the output takes even longer.
Running the ollama addon will give some hints:
Are there any plans to implement these drivers? One of the next kernels should also support NPUs. Are there any plans for Home Assistant?
Best regards
Marcus
What operating system image do you use?
generic-x86-64 (Generic UEFI capable x86-64 systems)
What version of Home Assistant Operating System is installed?
13.1
Did the problem occur after upgrading the Operating System?
No
Hardware details
Mini PC with:
AMD Ryzen 8845HS (Radeon 780M 4 - 16 GB, NPU)
64GB DDR5 RAM
1TB m2 SSD
Steps to reproduce the issue
Starting Ollama AddOn
Anything in the Supervisor logs that might be useful for us?
Anything in the Host logs that might be useful for us?
System information
No response
Additional information
No response
The text was updated successfully, but these errors were encountered: