--- title: Maximize AI Infrastructure Throughput by Consolidating... description: Production Kubernetes environments waste GPU resources when lightweight models like ASR and TTS occupy entire GPUs. This post benchmarks two GPU partitioning... canonical: https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Maximize AI Infrastructure Throughput by Consolidating Underutilized GPU Workloads | daily.dev og:description: Production Kubernetes environments waste GPU resources when lightweight models like ASR and TTS occupy entire GPUs. This post benchmarks two GPU partitioning... og:url: https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure og:image: https://api.daily.dev/og/posts/MkXWq3URE.png og:image:alt: Maximize AI Infrastructure Throughput by Consolidating Underutilized GPU Workloads og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Maximize AI Infrastructure Throughput by Consolidating Underutilized GPU Workloads **[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 8 min read · 2 upvotes · 0 comments ## Summary Production Kubernetes environments waste GPU resources when lightweight models like ASR and TTS occupy entire GPUs. This post benchmarks two GPU partitioning strategies—NVIDIA MIG (hardware-level) and time-slicing (software-level)—using a voice AI pipeline with ASR, TTS, and LLM workloads on three A100 GPUs. MIG achieved ~1.00 req/s per GPU with strict fault isolation, while time-slicing reached ~0.76 req/s but introduced noisy-neighbor risks. The recommendation is to use MIG for production workloads requiring reliability and throughput, and time-slicing for dev/CI environments. Consolidating support models onto a single partitioned GPU frees an entire GPU for additional LLM instances while maintaining >99% reliability. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Fractional GPUs and GPU Rightsizing: Stop Wasting Whole Cards](https://daily.dev/posts/fractional-gpus-and-gpu-rightsizing-stop-wasting-whole-cards-wjy0saqyp) · Cast AI · 1 upvotes · 0 comments - [Kubernetes GPU Optimization: How to Cut GPU Waste Without Slowing Workloads](https://daily.dev/posts/kubernetes-gpu-optimization-how-to-cut-gpu-waste-without-slowing-workloads-pi9fl1mnv) · Cast AI · 0 upvotes · 0 comments - [GPU Sharing in Kubernetes: How to Cut Costs and Boost GPU Utilization with Cast AI](https://daily.dev/posts/gpu-sharing-in-kubernetes-how-to-cut-costs-and-boost-gpu-utilization-with-cast-ai-hivlvubhj) · Cast AI · 0 upvotes · 0 comments --- Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#mlops](https://daily.dev/tags/mlops) [View this post on daily.dev](https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Maximize AI Infrastructure Throughput by Consolidating Underutilized GPU Workloads","url":"https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure"},"datePublished":"2026-03-25T16:36:50.668Z","dateModified":"2026-03-25T16:37:18.819Z","description":"Production Kubernetes environments waste GPU resources when lightweight models like ASR and TTS occupy entire GPUs. This post benchmarks two GPU partitioning...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2ff43e972c10748d378e9fe1eb65c51f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2ff43e972c10748d378e9fe1eb65c51f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes,mlops","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Maximize AI Infrastructure Throughput by Consolidating Underutilized GPU Workloads"}]} ```