PaletteAI Inference Launchpad Reference
Reference pages give you technical information when you need to look something up. They describe what exists and how it is configured, not how to accomplish a task.
Contents
| Reference | What it covers |
|---|---|
| Glossary | Definitions of the AI, product, and platform terms used across the docs. |
| Suggested Hardware | Compute, GPU, memory, storage, and network requirements for the appliance. |
| Bond Configuration | Field-by-field reference for the Local UI bond form used during installation. |
| Cluster Profile Variables | Every variable the Profile Config wizard collects, with types, defaults, and validation rules. |
| Certified Models by Hardware | Which models are certified for each supported NVIDIA and AMD GPU configuration. |
| Model Upload Reference | Palette CLI model download and upload flags, and the model metadata file fields. |
| Usage Metrics Reference | Every filter, metric, table column, and export field on the Usage page. |
| Thinking Directive Modes | Thinking modes and effort levels, per-engine interpretation, and console override states. |
| Claude Code Configuration | Environment variables and values for pointing Claude Code at the appliance. |
| Cursor Configuration | Settings and values for pointing Cursor at the appliance. |
| OpenAI Codex Configuration | Configuration file fields and values for pointing Codex at the appliance. |
| OpenCode Configuration | Configuration file fields and values for pointing OpenCode at the appliance. |
| Known Issues | Known installation issues and their workarounds, including HPE PCI enumeration. |