R
Runtipi•2mo ago
ABOhiccups

Ollama-NVIDIA won’t install

I got Minisforum MS-A2 with Yeston NVIDIA GeForce RTX 3050 6GB installed. I’ve tried to install Ollama-NVIDIA from Runtipi AppStore. It won’t install. I’ve followed instructions in description and it still won’t install Ollama-NVIDIA.
2 Replies
Skullky
Skullky•5w ago
Hello @ABOhiccups, Do you have more details on why the installation fails ? What does the Runtipi logs says ?
ABOhiccups
ABOhiccupsOP•4w ago
I’ve DM you with a error log file. 
sudo docker run --gpus all nvidia/cuda:12.1.1-runtime-ubuntu22.04 nvidia-smi
Unable to find image 'nvidia/cuda:12.1.1-runtime-ubuntu22.04' locally
12.1.1-runtime-ubuntu22.04: Pulling from nvidia/cuda
aece8493d397: Pull complete 
dd4939a04761: Pull complete 
b0d7cc89b769: Pull complete 
1532d9024b9c: Pull complete 
04fc8a31fa53: Pull complete 
a14a8a8a6ebc: Pull complete 
7d61afc7a3ac: Pull complete 
8bd2762ffdd9: Pull complete 
2a5ee6fadd42: Pull complete 
Digest: sha256:8bbc6e304b193e84327fa30d93eea70ec0213b808239a46602a919a479a73b12
Status: Downloaded newer image for nvidia/cuda:12.1.1-runtime-ubuntu22.04
docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: ldcache error: process /sbin/ldconfig terminated with signal 9
sudo docker run --gpus all nvidia/cuda:12.1.1-runtime-ubuntu22.04 nvidia-smi
Unable to find image 'nvidia/cuda:12.1.1-runtime-ubuntu22.04' locally
12.1.1-runtime-ubuntu22.04: Pulling from nvidia/cuda
aece8493d397: Pull complete 
dd4939a04761: Pull complete 
b0d7cc89b769: Pull complete 
1532d9024b9c: Pull complete 
04fc8a31fa53: Pull complete 
a14a8a8a6ebc: Pull complete 
7d61afc7a3ac: Pull complete 
8bd2762ffdd9: Pull complete 
2a5ee6fadd42: Pull complete 
Digest: sha256:8bbc6e304b193e84327fa30d93eea70ec0213b808239a46602a919a479a73b12
Status: Downloaded newer image for nvidia/cuda:12.1.1-runtime-ubuntu22.04
docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: ldcache error: process /sbin/ldconfig terminated with signal 9
It turns out. There was a bug with NVIDIA Driver not working with Docker on Arch Linux. I tested on Pop_OS and there’s no issue on Debian/Ubuntu. Update: NVIDIA Container Toolkit was fixed on Arch Linux!

Did you find this page helpful?