NVIDIA · Agent Runtime Infra
NVIDIA OpenShell, Snapshot and Kubernetes Engine
NVIDIA is donating OpenShell, an open-source runtime for securing and governing autonomous agents, to the Cloud Native Computing Foundation as a Sandbox project. It is also releasing NVIDIA Snapshot, an open-source component that restores checkpointed inference replicas without model reload or warmup. NVIDIA Kubernetes Engine and Kubernetes Recipes are in public preview for managed Kubernetes on GPU infrastructure. Design partner Saturn Cloud reported vLLM startup times falling from between 2 and 8.5 minutes to between 6 and 34 seconds.
Open the source ↗Similar Developer Tools releases
- TLX (Triton Low-Level Extensions)
Meta (Engineering at Meta) · GPU Kernel Extension · Week 47, 2026
- TPU 8tx and TPU 8i Max
Google · TPU Agent Infrastructure · Week 47, 2026
- NVIDIA Dynamo Recipes for Korean Open Models
NVIDIA · Dynamo Deployment Recipes · Week 47, 2026
- SageMaker Inference GPU partitioning (MIG)
Amazon Web Services (AWS Machine Learning Blog) · GPU Partitioning · Week 46, 2026
- Kinference
Buoyant · Inference Control Plane · Week 46, 2026
- Lutheos
Lutheos · Private inference API · Week 46, 2026
More from NVIDIA
- Agent Substrate
NVIDIA · Agent Sandbox Runtime · Week 47, 2026
- NVIDIA Alpamayo 2 Edge and AlpaJudge
NVIDIA · Driving VLA model · Week 47, 2026
- GR00T 2
NVIDIA · Open World Action Model · Week 47, 2026
- NVIDIA Dynamo Recipes for Korean Open Models
NVIDIA · Dynamo Deployment Recipes · Week 47, 2026
- NVIDIA Factory Operations Blueprint (FOX)
NVIDIA · Factory Manager Agent · Week 46, 2026
- STRATA (Earth-2 Checkpoints)
NVIDIA · Kilometre-scale weather emulator · Week 46, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.