Open access
Jul 2026
GPU Passthrough Across Virtualization Platforms for LLM Inference: Configuration Complexity and a Small-Model Performance Baseline
A structured, paired comparison of configuration complexity and performance across six platforms (Proxmox VM and LXC, native KVM, OpenStack VM and Zun, and Podman) on a single NVIDIA RTX 4500 Ada GPU, emphasizing the under-documented container paths
Priska Steininger, Manfred Pamsl, Helmut Lindner et al.
· Computers · 0 citations