llm-d | byteiota

Tag: llm-d

AI & Development

llm-d 1.0: Deploy Distributed AI Inference on Kubernetes

llm-d 1.0 is a Kubernetes-native distributed inference stack backed by IBM, Red Hat, Google and ...

2 days ago

Diagram of distributed Kubernetes inference nodes connected by a routing layer, representing llm-d 1.0 architecture

News

llm-d 1.0: The Inference Layer vLLM Was Missing

llm-d 1.0 shipped October 20 at PyTorch Conference. It turns a vLLM fleet into production ...

4 days ago

AI & Development

llm-d Joins CNCF: Kubernetes Gets Serious About AI Inference

llm-d from IBM, Red Hat, and Google joined CNCF. Here is what it does, why ...

August 11, 2026

Abstract visualization of llm-d distributed Kubernetes pods routing LLM inference requests with KV-cache-aware scheduling

News

llm-d 0.7: Kubernetes LLM Inference That Cuts GPU Waste

llm-d 0.7 is now a CNCF Sandbox project with AWS and Google behind it. Here's ...

June 1, 2026