FreeLLMNVIDIA DSX AI Factory adds AIBOM to GPU‑Kubernetes runtime for workload tracking
NVIDIA AI Cluster Runtime now integrates k8s‑aibom to inventory AI workloads on Kubernetes, improving visibility and compliance.
The integration creates CycloneDX 1.6 AIBOM records for supported AI workloads, automatically classifying categories and serving runtimes such as vLLM inference deployments.
During validation with AICR v1.2.0 and k8s‑aibom 1.6.2, the system generated about four API‑server requests per minute, used 2.2 millicores of CPU on average, and maintained a 28‑34 MiB controller memory working set.
AICR continues to generate version‑locked recipes and reproducible deployment bundles, while k8s‑aibom adds higher‑level workload discovery and traceability.
Qué significa para ti
The added inventory layer helps operators detect unregistered AI workloads, track model versions, and support security audits. For developers of free or locally hosted models, the visibility can guide compliance and ensure that runtime configurations match the intended AI assets.
Fuentes
- Validating GPU Platforms with Runtime AI Inventory via the NVIDIA DSX AI Factory, NVIDIA Developer (official), 11 Nov 2026
Escrito automáticamente a partir de las fuentes anteriores, luego revisado por nuestro código: cada número y nombre debe aparecer en ellas, y ninguna oración puede copiar una fuente. ¿Detectaste un error? Infórmalo.
¿Qué IA puedes usar gratis hoy?
Todos los modelos de IA gratuitos, clasificados por votos humanos ciegos, con la memoria y velocidad que necesita tu GPU.