Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

NEWS · CODING · #3441

NVIDIA AICR v1.2.0 integrates k8s-aibom 1.6.2 to emit CycloneDX AIBOMs for Kubernetes AI workloads

NVIDIA AI Cluster Runtime (AICR) v1.2.0 now includes a qualified AI bill of materials (AIBOM) integration based on the open-source k8s-aibom project (k8s-aibom v1.6.2). Two stock GKE recipes (h100-gke-cos-inference and h100-gke-cos-inference-dynamo) select k8s-aibom by default and other GKE recipes can opt in with --runtime-inventory; namespace opt-in controls reporting. The integration emits CycloneDX 1.6 AIBOM records with confidence tiers and evidence locators, and validation showed ~4 API-server requests/minute, ~2.2 millicores average CPU, and a 28–34 MiB controller memory working set in steady state.

KEY POINTS

  1. NVIDIA AI Cluster Runtime (AICR) v1.2.0 now includes a qualified AI bill of materials (AIBOM) integration based on the open-source k8s-aibom project (k8s-aibom v1.6.2).
  2. Two stock GKE recipes (h100-gke-cos-inference and h100-gke-cos-inference-dynamo) select k8s-aibom by default and other GKE recipes can opt in with --runtime-inventory; namespace opt-in controls reporting.
  3. The integration emits CycloneDX 1.6 AIBOM records with confidence tiers and evidence locators, and validation showed ~4 API-server requests/minute, ~2.2 millicores average CPU, and a 28–34 MiB controller memory working set in steady state.

WHY IT MATTERS

This links platform-level, version-locked GPU runtime recipes (AICR) with runtime workload discovery (k8s-aibom), improving traceability and governance of what AI code and models actually run in Kubernetes clusters.

SOURCES & TIMELINE

1