Manage NVIDIA GR00T model deployment, finetuning, and inference on Nebius clusters.
npx skills add https://github.com/nebius/nebius-physical-ai --skill groot
Please help me install this Agent Skill. Skill: groot Source: https://github.com/nebius/nebius-physical-ai/tree/main/skills/tools/groot Command: npx skills add https://github.com/nebius/nebius-physical-ai --skill groot
This Skill streamlines the complex lifecycle of NVIDIA GR00T robot foundation models, removing the friction from model deployment, finetuning, and infrastructure alignment on Nebius clusters.
Use the groot skill to deploy the latest robot foundation model checkpoint to the configured Nebius cluster.
High-intent search queries and answers about installing and using this skill.
To deploy NVIDIA GR00T robot foundation models, you can use this Skill to automate artifact staging, environment configuration, and deployment routing on Nebius infrastructure. It manages the end-to-end process of downloading, converting, and serving GR00T checkpoints.
Finetuning GR00T checkpoints involves handling model artifacts from NGC or Hugging Face registries and performing checkpoint conversion. This Skill streamlines that lifecycle while maintaining strict credential security and aligning GPU resources for the finetuning process.
Yes, you can use Nebius infrastructure to run operational validation for robot foundation models. This Skill provides built-in status checks, system information retrieval, and ingress management to ensure your deployed models are running correctly across the cluster.
Yes, integrating with NGC and Hugging Face registries requires valid credentials to download and manage GR00T model artifacts. This Skill handles the checkpoint conversion and deployment while maintaining strict credential security throughout the process.
The best way to convert and serve GR00T checkpoints for inference is to automate the artifact staging and environment configuration. This Skill orchestrates checkpoint conversion and cluster-wide deployment routing to get your model live on Nebius infrastructure.
nebiusConfigure the Cosmos3 framework by validating source repositories and staging model checkpoints.
dmzoneillBenchmark local Ollama inference with status checks and response time tests.
Lobbi-DocsAutomate Kubernetes deployment, management, and troubleshooting workflows.
OgenticAIOrchestrate software development from Linear tickets to deployment with human checkpoints.
