Search results for query: nvidia-smi

Your issue isn't the Nvidia driver; it's a repository conflict. You are trying to install dependencies for Intel GPUs on a system meant for Nvidia. The error level-zero-dev comes from the Intel repositories listed in your apt update log (Hit:4 and Hit:5). This is breaking your package manager.

...so I added non-free and tried the Debian NVIDIA packages: apt-get install --no-install-recommends nvidia-kernel-dkms nvidia-driver-bin nvidia-smi nvidia-modprobe DKMS fails when building nvidia-current/550.163.01 for 6.17.4-1-pve. DKMS error snippet It fails in nvidia-drm with DRM API...

...NVIDIA Corporation GP107GL [Quadro P620] [10de:1cb6] (rev a1) Subsystem: Dell Device [1028:1264] Kernel driver in use: nvidia nvidia-smi +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.119.02 Driver Version...

...NVIDIA Corporation GP107GL [Quadro P620] [10de:1cb6] (rev a1) Subsystem: Dell Device [1028:1264] Kernel driver in use: nvidia nvidia-smi +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.119.02 Driver Version...

...the Nvidia proprietary setup about a missing x - config file and a recommendation to install pkg-config. Regardless, I pushed through and nvidia-smi or NVtop displayed the gpus and all seemed well, or so I thought. I next passed through the driver into OpenWebUI LXC created from the Proxmox...

Hello, @jwelvaert: Can you test this method. Proxmox Host Information: Group : 195, 234, 237 /etc/pve/lxc/100.conf LXC: (Debian 12 / Kernel 6.8.12-17-pve)

Hi, Did you turn on SR-IOV in BIOS? I assigned 2 gpus to resources mapping in datacenter. And I added 2 gpus to VM. Finally, I could see 2 gpus by nvidia-smi in ubuntu 24.04 server VM.

Hi, Did you turn on SR-IOV in BIOS? I assigned 2 gpus to resources mapping in datacenter. And I added 2 gpus to VM. Finally, I could see 2 gpus by nvidia-smi in ubuntu 24.04 server VM.

...but for Nvidia. Maybe you could try pci=noaer as they outline here: https://github.com/NVIDIA/open-gpu-kernel-modules/pull/981#issuecomment-3621315260. and here https://egpu.io/forums/thunderbolt-linux-setup/rtx-5080-via-thunderbolt-5-egpu-hard-lock-on-cuda-operations-nvidia-smi-works-at-idle/

Yes this is how it worked with multiple nvidia GPU's that have passed through this machine except the display would change to the guest os, with the AMD GPU the display remains on with the host dialogue and frozen cursor. Output is attached below, I did update the script to my device's PCI ID...

Just done exactly that for a customer ;) Not tested yet, bit nvidia-smi sees the card inside the container, so i think it will work additional lxc-config entries: lxc.cgroup2.devices.allow: c 195:* rwm lxc.cgroup2.devices.allow: c 234:* rwm lxc.cgroup2.devices.allow: c 509:* rwm...

...DPP to train a model, the execution fails with: CUDA error: operation not supported. The vGPU license was active at the time of testing: nvidia-smi -q | grep "License Status" License Status : Licensed (Expiry: 2025-11-22 6:1:40 GMT) As a matter of fact, we tried...

...+ OVMF) Guest OS: • Ubuntu 22.04 • Ubuntu 24.04 • NVIDIA driver 580.95.05 • CUDA 13.0 Result: Both GPUs passed through successfully. nvidia-smi nvlink --status shows all 18× NVLink lanes active per GPU (26.562 GB/s each), meaning full NVLink (NV18) is functional inside a VM. Measured...

...APUs von AMD gibt finde ich es eigentlich charmant von Docker im LXC bist zu Host Transparent sehen zu können was mit Ollama/LLMs/CUDA/Nvidia-smi passiert. Bei dieser Lösung, die eine valide Alternative ist, gibt es keine sinnlose Bindung von GPUs an Audio-Devices die alles brechen wenn man...

...550.163.02.patch. Installed vgpu-unlock-rs from https://github.com/mbilker/vgpu_unlock-rs. Rebooted, and viola, have P40 profiles :) nvidia-smi Wed Nov 12 08:12:24 2025 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 550.163.02...

you want to change the line in vgpu_unlock-rs/src/lib.rs on 370-377 where it says Tesla T4 and gives a hex code, change the 1EB8 to 1EB9 for the edition of the T4 with 32GB (cant find anything about the card itself as a 32gb edition but a few lists give that option or list it as a quadro 6000...

...16GB. When I go to create a 3rd VM, it says I have zero devices available for 8GB (two VM's are currently running with nvidia-233): nvidia-smi vgpu Tue Nov 11 17:09:58 2025 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 550.144.02...

...> /sys/bus/pci/devices/$DEV/driver_override done fi modprobe -i vfio-pci And this works! ...for about 5 minutes. At first, nvidia-smi returns real values. After that, I start getting: root@pve:~# nvidia-smi Tue Nov 11 15:41:31 2025...

...per @zenowl77 with a proxmox 8.4 vm, but getting same results: Patched and got 'NVIDIA-Linux-x86_64-570.172.07-vgpu-kvm-custom.run' Both nvidia-smi calls return showing gpus, but mdevctl types is blank. Here's what dmesg showing: dmesg -T | grep vgpu [Sat Nov 8 19:38:15 2025]...

...P6000 and a Titan Xp. I've patched 16.9 NVIDIA-Linux-x86_64-535.230.02-vgpu-kvm-custom.run with 535.230.02.patch, it installs fine, nvidia-smi returns both cards, as well as nvidia-smi vgpu, but nothing in medctl. nvidia-smi Sat Nov 8 18:36:23 2025...