--- title: Understanding disaggregated GenAI model serving with llm-d description: llm-d is an open source, cloud-native system for high-scale LLM deployments that addresses latency and memory-bandwidth bottlenecks by disaggregating the... canonical: https://daily.dev/posts/understanding-disaggregated-genai-model-serving-with-llm-d-lvuvnpaha twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Understanding disaggregated GenAI model serving with llm-d | daily.dev og:description: llm-d is an open source, cloud-native system for high-scale LLM deployments that addresses latency and memory-bandwidth bottlenecks by disaggregating the... og:url: https://daily.dev/posts/understanding-disaggregated-genai-model-serving-with-llm-d-lvuvnpaha og:image: https://api.daily.dev/og/posts/LvUvNPaHa.png og:image:alt: Understanding disaggregated GenAI model serving with llm-d 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. # Understanding disaggregated GenAI model serving with llm-d **[Ubuntu](https://daily.dev/sources/ubuntu)** · 4 min read · 1 upvotes · 0 comments ## Summary llm-d is an open source, cloud-native system for high-scale LLM deployments that addresses latency and memory-bandwidth bottlenecks by disaggregating the inference workload across dedicated hardware. It splits processing into four Kubernetes-managed components: an inference scheduler (adaptive load balancer using Prometheus metrics), a KV cache manager, a prefill worker for compute-intensive prompt processing, and a decode worker for token generation. The post explains why organizations with data sovereignty requirements would self-host LLMs, highlights the availability of competitive open-weight models, and shares experimental Juju charms the author built to simplify llm-d deployments on Ubuntu without requiring deep Kubernetes expertise. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Introduction to distributed inference with llm-d](https://daily.dev/posts/introduction-to-distributed-inference-with-llm-d-ed6jsysii) · Red Hat Developer · 0 upvotes · 0 comments - [Disaggregation in Large Language Models: The Next Evolution in AI Infrastructure](https://daily.dev/posts/disaggregation-in-large-language-models-the-next-evolution-in-ai-infrastructure-i3bji5n2f) · InfoQ · 0 upvotes · 0 comments --- Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/understanding-disaggregated-genai-model-serving-with-llm-d-lvuvnpaha) ```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":"Understanding disaggregated GenAI model serving with llm-d","url":"https://daily.dev/posts/understanding-disaggregated-genai-model-serving-with-llm-d-lvuvnpaha","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/understanding-disaggregated-genai-model-serving-with-llm-d-lvuvnpaha"},"datePublished":"2026-04-27T13:19:53.944Z","dateModified":"2026-04-27T13:20:29.768Z","description":"llm-d is an open source, cloud-native system for high-scale LLM deployments that addresses latency and memory-bandwidth bottlenecks by disaggregating the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7500f876e087b5305427301ab10232e1?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7500f876e087b5305427301ab10232e1?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ubuntu","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":"Ubuntu","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/e9ae7e11e4574c27a37fcd23062e723e","url":"https://daily.dev/sources/ubuntu"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/understanding-disaggregated-genai-model-serving-with-llm-d-lvuvnpaha","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes,llm","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ubuntu","item":"https://daily.dev/sources/ubuntu"},{"@type":"ListItem","position":3,"name":"Understanding disaggregated GenAI model serving with llm-d"}]} ```