Mark Achtemichuk talks with Uday Kulkurne about the performance of virtualized Machine Learning and AI workloads on different NVIDIA GPUs.
Links to additional resources:
Power of Virtualized ML/AI delivers near bare metal performance with ML Perf Inference 4.0 – https://blogs.vmware.com/performance/2024/05/magic-of-virtualized-ml-ai.html
The Magic of Virtualized Machine Learning and AI – https://blogs.vmware.com/performance/2024/05/magic-of-virtualized-ml-ai.html
ML Perf Inference v3.0 Performance Using NVIDIA GPUs on VMware vSphere 8 – https://blogs.vmware.com/performance/2023/04/no-virtualization-tax-for-mlperf-inference-v3-0-using-nvidia-hopper-and-ampere-vgpus-and-nvidia-ai-software-with-vsphere-8-0-1.html
VMware vSphere 8 Performance is in the Goldilocks Zone for AI/ML Training and Inference – https://blogs.vmware.com/performance/2023/08/extreme-performance-series-2023-vsphere-is-the-goldilocks-zone-for-machine-learning-and-ai-workloads.html
VMware Explore 2024 – https://www.vmware.com/explore/us
Extreme Performance Series 2024 – https://blogs.vmware.com/performance/2024/08/extreme-performance-video-blog-series-2024.html
