--- title: llm-d joins the CNCF as a Kubernetes-native framework... description: Red Hat, IBM Research, and Google Cloud have donated llm-d to the CNCF as a Sandbox project, positioning it as a Kubernetes-native framework for distributed... canonical: https://daily.dev/posts/llm-d-joins-the-cncf-as-a-kubernetes-native-framework-for-distributed-llm-inference-tdsbxmmjt twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: llm-d joins the CNCF as a Kubernetes-native framework for distributed LLM inference | daily.dev og:description: Red Hat, IBM Research, and Google Cloud have donated llm-d to the CNCF as a Sandbox project, positioning it as a Kubernetes-native framework for distributed... og:url: https://daily.dev/posts/llm-d-joins-the-cncf-as-a-kubernetes-native-framework-for-distributed-llm-inference-tdsbxmmjt og:image: https://api.daily.dev/og/posts/tdsbXMmJT.png og:image:alt: llm-d joins the CNCF as a Kubernetes-native framework for distributed LLM inference 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. # llm-d joins the CNCF as a Kubernetes-native framework for distributed LLM inference **[Collections](https://daily.dev/sources/collections)** · 3 min read · 2 upvotes · 0 comments ## Summary Red Hat, IBM Research, and Google Cloud have donated llm-d to the CNCF as a Sandbox project, positioning it as a Kubernetes-native framework for distributed LLM inference at production scale. llm-d fills the gap between high-level control planes like KServe and low-level engines like vLLM by providing prefill/decode disaggregation, KV-cache-aware routing, inference-aware autoscaling, and hardware-agnostic serving across NVIDIA, AMD, Intel, and Google TPUs. Early benchmarks on Qwen3-32B show ~120,000 tokens/second throughput with near-zero time-to-first-token, and Google Cloud reported 2x improvements in time-to-first-token versus standard Kubernetes services. The CNCF also published Kubernetes AI Requirements (KARs) v1.35 mandating stable in-place pod resizing and workload-aware scheduling, with 31 certified platforms currently. The project's roadmap includes multi-modal workloads, multi-LoRA optimization, and deeper vLLM integration. ## Content ## What happened At KubeCon + CloudNativeCon Europe 2026, Red Hat, IBM Research, and Google Cloud donated llm-d to the CNCF as a Sandbox project. Originally launched in May 2025 by Red Hat, Google Cloud, IBM Research, CoreWeave, and NVIDIA, llm-d is an open-source framework for running LLM inference as a distributed, production-grade workload on Kubernetes. The donation came alongside a broader CNCF push to make Kubernetes a serious platform for AI inference. The foundation published Kubernetes AI Requirements (KARs) v1.35, which now mandates stable in-place pod resizing and workload-aware scheduling. The KAR program currently counts 31 certified platforms, and a "Verify Conformance Bot" for third-party validation is in the works. ## What llm-d actually does The project targets a specific gap: the space between high-level control planes like KServe and low-level inference engines like vLLM. Running a large model on a single GPU node works fine at small scale, but production inference needs to spread across multiple accelerators and adapt to shifting load — and vanilla Kubernetes wasn't built for that. llm-d addresses this with a few concrete capabilities: - **Prefill/decode disaggregation** — the two phases of LLM inference run on separate nodes and scale independently, so a spike in new requests doesn't starve ongoing generation - **KV-cache-aware routing** — traffic is directed based on what's already cached, reducing redundant computation - **Inference-aware autoscaling** — the scheduler accounts for both traffic patterns and hardware characteristics, not just CPU/memory - **Hardware-agnostic serving** — works across NVIDIA, AMD, Intel, and Google TPUs It builds on vLLM and integrates with the Kubernetes Gateway API Inference Extension and LeaderWorkerSet. ## Early numbers Benchmarks from the v0.5 release on Qwen3-32B show near-zero time-to-first-token and roughly 120,000 tokens per second throughput, compared to rapid degradation under load with a standard Kubernetes service. Google Cloud's internal testing reported 2x improvements in time-to-first-token. The project also aims to establish open, reproducible inference benchmarks as a neutral industry standard — something the ecosystem currently lacks. ## Who's involved Founding collaborators beyond the three donors include NVIDIA, CoreWeave, AMD, Cisco, Hugging Face, Intel, Lambda, and Mistral AI. ## What's next The CNCF is also tracking related ecosystem work: AWS's Kube Resource Orchestrator (KRO), the Kueue job queueing system, and NVIDIA's open-source AI Cluster Runtime (AICR). Future KAR standards for Sovereign AI are planned, and llm-d's own roadmap targets multi-modal workloads, multi-LoRA optimization, and deeper vLLM integration. CNCF executive director Jonathan Bryce has been direct about the direction: Kubernetes should become the dominant platform for AI inference, including edge deployments running smaller models. ## Similar posts on daily.dev - [Combining KServe and llm-d for optimized generative AI inference](https://daily.dev/posts/combining-kserve-and-llm-d-for-optimized-generative-ai-inference-emjdf7e1n) · Red Hat Developer · 0 upvotes · 0 comments - [Master KV cache aware routing with llm-d for efficient AI inference](https://daily.dev/posts/master-kv-cache-aware-routing-with-llm-d-for-efficient-ai-inference-5es7qcvqr) · Red Hat Developer · 0 upvotes · 0 comments --- Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#distributed-systems](https://daily.dev/tags/distributed-systems), [#cncf](https://daily.dev/tags/cncf), [#vllm](https://daily.dev/tags/vllm) [View this post on daily.dev](https://daily.dev/posts/llm-d-joins-the-cncf-as-a-kubernetes-native-framework-for-distributed-llm-inference-tdsbxmmjt) ```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":"llm-d joins the CNCF as a Kubernetes-native framework for distributed LLM inference","url":"https://daily.dev/posts/llm-d-joins-the-cncf-as-a-kubernetes-native-framework-for-distributed-llm-inference-tdsbxmmjt","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/llm-d-joins-the-cncf-as-a-kubernetes-native-framework-for-distributed-llm-inference-tdsbxmmjt"},"datePublished":"2026-03-24T15:28:02.420Z","dateModified":"2026-03-25T08:12:12.950Z","description":"Red Hat, IBM Research, and Google Cloud have donated llm-d to the CNCF as a Sandbox project, positioning it as a Kubernetes-native framework for distributed...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4fd3622ec758aa6f46a5d51275d8be2e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4fd3622ec758aa6f46a5d51275d8be2e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collections","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":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/llm-d-joins-the-cncf-as-a-kubernetes-native-framework-for-distributed-llm-inference-tdsbxmmjt","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes,distributed-systems,cncf,vllm","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"llm-d joins the CNCF as a Kubernetes-native framework for distributed LLM inference"}]} ```