Distributed inference is becoming a standard cloud native workload.
#llmd has joined the #CNCF Sandbox, bringing Kubernetes-native routing, orchestration, and disaggregated serving to AI inference.

Learn more: https://www.cncf.io/blog/2026/03/24/welcome-llm-d-to-the-cncf-evolving-kubernetes-into-sota-ai-infrastructure/
#Kubernetes #AI #CloudNative #CNCF

Welcome llm-d to the CNCF: Evolving Kubernetes into SOTA AI infrastructure

We are thrilled to announce that llm-d has officially been accepted as a Cloud Native Computing Foundation (CNCF) Sandbox project! As generative AI transitions from research labs to productionโ€ฆ

CNCF

AI at the edge is an infrastructure puzzle. Red Hat is helping solve it by contributing llm-d to the #CNCF, establishing "well-lit paths" for AI-RAN orchestration with SoftBank. ๐Ÿง

This is about optimizationโ€”making inference a first-class citizen alongside traditional containers.

Proud to see Red Hat continuing our legacy of open-source leadership, from #Kubernetes and #etcd to #KEDA and now #llmd.

Read more: https://www.redhat.com/en/blog/how-llm-d-brings-critical-resource-optimization-softbanks-ai-ran-orchestrator

#RedHat #AI #OpenSource #KubeCon #CloudNative

How llm-d brings critical resource optimization with SoftBankโ€™s AI-RAN orchestrator

In Red Hatโ€™s latest collaboration with SoftBank Corp., we have integrated llm-d into SoftBankโ€™s AI-RAN orchestrator, AITRAS.

Red Hat is contributing llm-d to the #CNCF, turning fragmented AI into modular, interoperable microservices. ๐Ÿง

The goal? Make AI inference a first-class citizen in the same cloud-native environment as your traditional apps.

I love how Red Hat continues to fuel the #OpenSource ecosystem. From our roots in #Kubernetes and #etcd to newer projects like #KEDA and #CRI-O, weโ€™re committed to building "well-lit paths" for everyone.

#RedHat #KubeCon #CloudNativeCon #AI #llmd

https://www.redhat.com/en/blog/why-were-contributing-llm-d-cncf-standardizing-future-ai?sc_cid=701f2000000txokAAA&utm_source=bambu&utm_medium=organic_social

Why weโ€™re contributing llm-d to the CNCF: Standardizing the future of AI

Red Hat is contributing llm-d to the Cloud Native Computing Foundation (CNCF) as a Sandbox project to standardize high-performance, distributed AI inference serving within the cloud-native stack. This contribution aims to bridge the capabilities gap between AI experimentation and production by providing a specialized data-plane orchestration layer that maximizes infrastructure efficiency and enables flexible deployment on any choice of hardware.

Red Hat AI | 3 | Red Hat Documentation

Red Hat AI | 3 | Red Hat Documentation

3 things to know about Red Hat AI 3

YouTube
Big thanks to everyone contributing code, reviews, and ideas โ€” this integration is shaping up to be a game-changer for ๐—ž๐˜‚๐—ฏ๐—ฒ๐—ฟ๐—ป๐—ฒ๐˜๐—ฒ๐˜€-๐—ป๐—ฎ๐˜๐—ถ๐˜ƒ๐—ฒ ๐—Ÿ๐—Ÿ๐—  ๐˜€๐—ฒ๐—ฟ๐˜ƒ๐—ถ๐—ป๐—ด. Stay tuned for next release! #KServe #llmd #GenerativeAI #MLOps #Kubernetes #ModelServing #AIInfrastructure

Big thanks to everyone contributing code, reviews, and ideas โ€” this integration is shaping up to be a game-changer for ๐—ž๐˜‚๐—ฏ๐—ฒ๐—ฟ๐—ป๐—ฒ๐˜๐—ฒ๐˜€-๐—ป๐—ฎ๐˜๐—ถ๐˜ƒ๐—ฒ ๐—Ÿ๐—Ÿ๐—  ๐˜€๐—ฒ๐—ฟ๐˜ƒ๐—ถ๐—ป๐—ด. Stay tuned for next release!

#KServe #llmd #GenerativeAI #MLOps #Kubernetes #ModelServing #AIInfrastructure

Red Hat Launches the llm-d Community, Powering Distributed Gen AI Inference at Scale

Red Hat has launched llm-d, a new open source project developed in collaboration with industry leaders, designed to power distributed generative AI inference at scale. The project utilizes Kubernetes architecture, vLLM-based distributed inference, and intelligent AI-aware network routing to enable robust and scalable large language model (LLM) inference clouds.

๐ŸŽ‰ Behold! The #llmd #community emerges from the depths of the #tech abyss, promising the holy grail of Kubernetes-native distributed #LLM #inference. ๐Ÿค– Because who doesn't want their #AI #deployments served with extra buzzwords and a side of "competitive performance per dollar"? ๐Ÿฝ๏ธ
https://llm-d.ai/blog/llm-d-announce #Kubernetes #news #HackerNews #ngated
Announcing the llm-d community! | llm-d

Debut announcement of llm-d project and community