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.
あなたにとっての意味
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.
ソース
- Validating GPU Platforms with Runtime AI Inventory via the NVIDIA DSX AI Factory, NVIDIA Developer (official), 11 Nov 2026
上記のソースから自動的に生成し、当社のコードでチェックしました：すべての数値と名前が含まれ、文がソースをコピーしてはいけません。間違いを見つけましたか？報告する。
今日無料で使えるAIはどれですか？
すべての無料AIモデルをブラインドヒューマン投票で順位付けし、あなたのGPUで必要なメモリと速度を示します。