Skip to main content
Version: v1.4.x

Featured Profile Bundles

This page covers the curated, ready-to-use Profile Bundles from PaletteAI Studio, along with the built-in Profile Bundles that ship with a PaletteAI install. Use these reference pages for stack-specific guidance beyond the general Create and Manage Profile Bundles and Import Profile Bundles tasks.

What these pages include​

Each Profile Bundle page typically covers:

  • Overview — What the stack is and how PaletteAI packages it as a Profile Bundle
  • Compatibility — Validated Kubernetes, PaletteAI, and upstream product versions (when published under a partner program)
  • How it fits PaletteAI — Bundle type (Application, Infrastructure, or Fullstack), Compute Pool and App Deployment roles
  • Get the Profile Bundle — Prerequisites, download from PaletteAI Studio, and import through the PaletteAI UI
  • Deploy — Deploying the bundle onto a Compute Pool (for example as an App Deployment)
  • Validate — Checks that confirm the import and deployment succeeded

Exact steps and version matrices differ by product. Refer to the individual page for details.

  • AI Launchpad — A Fullstack Profile Bundle that turns a Compute Pool into a Launchpad-enabled cluster, exposing vLLM-backed Model Deployments through an OpenAI-compatible gateway with unified authentication, quotas, and Token Metering.
  • NVIDIA Run:ai — GPU orchestration and scheduling for AI/ML workloads on PaletteAI Compute Pools
  • VMO Profile Bundle — A built-in Profile Bundle that installs a Virtual Machine Orchestrator (VMO) stack on a Compute Pool so that the pool can run AI Virtual Machines. Unlike the bundles above, it ships with a PaletteAI install rather than being downloaded from PaletteAI Studio. It carries the palette.ai/infra-kind: vm label, which is how a Compute Pool is identified as able to run AI Virtual Machines.