# vgpu time-slicing

Published articles for vgpu time-slicing.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How VMware Cloud Foundation Uses vGPU Time-Slicing to Improve Inference Throughput

DevFeed: [How VMware Cloud Foundation Uses vGPU Time-Slicing to Improve Inference Throughput](<https://devfeed.tech/articles/optimizing-ai-deployments-with-vmware-cloud-foundation-part-4-87548.md>)

Original publisher: [Read original article](<https://blogs.vmware.com/cloud-foundation/2026/10/14/optimizing-ai-deployments-with-vmware-cloud-foundation-part-4/>)

Author: vmwareblogs

Published: 2026-10-14T21:53:33Z

Content type: article

Language: en

Sources: [VMware](<https://devfeed.tech/sources/vmware-blogs.md>)

Topics: [VMware Cloud Foundation](<https://devfeed.tech/topics/vcf-9-1.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [NVIDIA NIM](<https://devfeed.tech/topics/nvidia-nim.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [gpu-utilization](<https://devfeed.tech/tags/gpu-utilization.md>), [home-page](<https://devfeed.tech/tags/home-page.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mig](<https://devfeed.tech/tags/mig.md>), [optimizing](<https://devfeed.tech/tags/optimizing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pipeline-parallelism](<https://devfeed.tech/tags/pipeline-parallelism.md>), [tensor-parallelism](<https://devfeed.tech/tags/tensor-parallelism.md>), [tensorrt-llm](<https://devfeed.tech/tags/tensorrt-llm.md>), [throughput](<https://devfeed.tech/tags/throughput.md>), [vcf](<https://devfeed.tech/tags/vcf.md>), [vcf-9-0](<https://devfeed.tech/tags/vcf-9-0.md>), [vcf-9-1](<https://devfeed.tech/tags/vcf-9-1.md>), [vgpu-time-slicing](<https://devfeed.tech/tags/vgpu-time-slicing.md>), [vmware-cloud-foundation](<https://devfeed.tech/tags/vmware-cloud-foundation.md>), [vsphere](<https://devfeed.tech/tags/vsphere.md>)

### AI overview

The article describes how NVIDIA vGPU time-slicing on VMware Cloud Foundation can improve aggregate AI inference throughput by letting workloads use compute cycles left idle by other workloads. It reports gains of up to 30% for unoptimized Hugging Face models and about 10% for TensorRT-LLM models, while noting that the benefit decreases as workloads are optimized and disappears when no idle cycles remain.

### Source excerpt

Utilizing Time-slicing to Optimize Inference Throughput Introduction The Broadcom Performance team has completed extensive performance tests demonstrating VCF's efficiency and flexibility for running AI workloads in various configurations. To explain our results, we've published a white paper and a series of four blogs: Part 1: Maximizing Performance, Efficiency, and Flexibility in Multi-tenant Environment Part 2: ... Continued The post Optimizing AI Deployments with VMware Cloud Foundation (Part 4) appeared first on VMware Blogs.