Avatar photo
By: Ivan Tarin

March 24, 2026 8:00 am

660 views

Unlock AI Efficiency with NVIDIA MIG vGPU Multitenancy on Kubernetes with SUSE Virtualization

What is NVIDIA MIG NVIDIA Multi-Instance GPU (MIG) technology allows a single physical GPU to be partitioned into multiple isolated instances, enabling several workloads to run concurrently with dedicated compute and memory resources. MIG improves GPU utilisation and supports secure multi-tenant AI workloads. GPU capacity is one of the most expensive and constrained resources in […]

Read More


Avatar photo
By: Erico Mendonca

December 26, 2025 7:52 pm

1,467 views

PCI Passthrough Demystified: Setting up AMD GPUs in Harvester

If you’ve ever tried to set up GPU passthrough, you know the struggle.You edit the GRUB config, you isolate the IOMMU groups, you cross your fingers, and... you get a black screen. Or worse, the dreaded "Code 43."Setting up PCI passthrough is notoriously finicky, and doing it within a Hyper-Converged […]

Read More


Avatar photo
By: Christian Hüller

October 4, 2024 10:41 am

7,680 views

Generating images with LocalAI using a GPU

  Introduction In my last blog post on using code generating LLMs on OpenSUSE, I explained on how to run models on your local machine without utilizing a GPU card. In this post I want to show on how to setup your system in order to make use of an available GPU for running […]

Read More


Avatar photo
By: Pranay Bakre

April 20, 2021 5:06 am

13,442 views

AI at the Edge with K3s and NVIDIA Jetson Nano: Object Detection and Real-Time Video Analytics

With the advent of new and powerful GPU-capable devices, the possible use cases that we can execute at the edge are expanding. The edge is growing in size and getting more efficient as technology advances. NVIDIA, with its industry-leading GPUs, and Arm, the leading technology provider of processor IP, […]

Read More


Avatar photo
By: Jay Kruemcke

October 12, 2020 2:49 pm

16,317 views

Simplified access to the NVIDIA CUDA toolkit on SUSE Linux for HPC

Overview The High-Performance Computing industry is rapidly embracing the use of AI and ML technology in addition to legacy parallel computing. Heterogeneous Computing, the use of both CPUs and accelerators like graphics processing units (GPUs), has become increasingly more common and GPUs from NVIDIA are the most popular accelerators used today for AI/ML workloads. To […]

Read More