Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #29356

Dynamo

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

CODING · 1 SOURCE · NVIDIA Developer

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.

6.0

MODELS · 1 SOURCE · NVIDIA Developer

NVIDIA outlines NVFP4, Vera Rubin platform, and five co-design levers to boost AI throughput and KV-cache efficiency

In a blog post, NVIDIA says it is using five co-designed levers — the 4-bit NVFP4 numerical format, wide expert parallelism in TensorRT-LLM, Dynamo (fleet-aware KV-cache routing and the KV Cache Runner), the Vera CPU with Rubin interconnect, and a CMX pod-level storage tier — to free HBM, raise arithmetic intensity, and improve throughput for agentic inference. NVIDIA reports NVFP4 reduces model footprint roughly 3.5x versus FP16 (1.8x versus FP8), NVFP4 KV cache halves cache footprint versus FP8, and claims the Vera Rubin NVL72 can deliver up to 30x the throughput per megawatt of GB300 NVL72 on an agentic benchmark.

8.0