--- title: Unlock Massive Token Throughput with GPU Fractioning in... description: NVIDIA and Nebius AI Cloud jointly benchmarked GPU fractioning via NVIDIA Run:ai to evaluate LLM inference performance at scale. Using NVIDIA NIM microservices... canonical: https://daily.dev/posts/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-run-ai-lsirfcvwp twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai | daily.dev og:description: NVIDIA and Nebius AI Cloud jointly benchmarked GPU fractioning via NVIDIA Run:ai to evaluate LLM inference performance at scale. Using NVIDIA NIM microservices... og:url: https://daily.dev/posts/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-run-ai-lsirfcvwp og:image: https://api.daily.dev/og/posts/LsiRfCVWP.png og:image:alt: Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai 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. # Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai **[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 11 min read · 0 upvotes · 0 comments ## Summary NVIDIA and Nebius AI Cloud jointly benchmarked GPU fractioning via NVIDIA Run:ai to evaluate LLM inference performance at scale. Using NVIDIA NIM microservices on H100 NVL and HGX B200 clusters, results show 0.5 GPU fractions deliver 77% of full-GPU token throughput and 86% of concurrent user capacity with TTFT under 1 second. Quarter-GPU fractions on smaller models like Phi-4-Mini enabled up to 72% more concurrent users. Mixed-workload co-location (chat, reasoning, embeddings) on shared GPUs achieved up to 3x more total system users. Autoscaling from 1 to 16 replicas showed no latency spikes or error rates, validating fractional GPU scheduling as a production-ready strategy for maximizing GPU ROI. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Maximizing GPU Utilization with NVIDIA Run:ai and NVIDIA NIM](https://daily.dev/posts/maximizing-gpu-utilization-with-nvidia-run-ai-and-nvidia-nim-c0kc79bdr) · NVIDIA Developer · 0 upvotes · 0 comments - [Maximize AI Infrastructure Throughput by Consolidating Underutilized GPU Workloads](https://daily.dev/posts/maximize-ai-infrastructure-throughput-by-consolidating-underutilized-gpu-workloads-mkxwq3ure) · NVIDIA Developer · 2 upvotes · 0 comments - [Scaling Token Factory Revenue and AI Efficiency by Maximizing Performance per Watt](https://daily.dev/posts/scaling-token-factory-revenue-and-ai-efficiency-by-maximizing-performance-per-watt-2qzgn7uql) · NVIDIA Developer · 0 upvotes · 0 comments --- Tags: [#kubernetes](https://daily.dev/tags/kubernetes) [View this post on daily.dev](https://daily.dev/posts/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-run-ai-lsirfcvwp) ```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":"Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai","url":"https://daily.dev/posts/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-run-ai-lsirfcvwp","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-run-ai-lsirfcvwp"},"datePublished":"2026-02-18T18:03:02.536Z","dateModified":"2026-02-18T18:03:25.357Z","description":"NVIDIA and Nebius AI Cloud jointly benchmarked GPU fractioning via NVIDIA Run:ai to evaluate LLM inference performance at scale. Using NVIDIA NIM microservices...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4d7923ff861e9306ea858283a203b28d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4d7923ff861e9306ea858283a203b28d?_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/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-run-ai-lsirfcvwp","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes","timeRequired":"PT11M"} {"@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":"Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai"}]} ```