TECH RADAR / SYSTEMS & CACHING
llm-d
Kubernetes-native distributed inference.
What it covers
Deployment paths, distributed serving, and inference-aware orchestration.
What we would check
Start from a documented deployment recipe and retain its engine, scheduler, hardware, and Kubernetes versions.
Go to the source
A curated ecosystem entry. The evaluation guidance is our interpretation, not a report of a completed test or a performance ranking.