Skip to main content

PaletteAI Inference Launchpad How-to Guides

How-to guides get a specific job done on a running appliance. They assume you know what you want to accomplish and give you the steps to do it without teaching background concepts.

Contents​

GuideWhat you do
Install the ApplianceFlash the installer ISO, boot the hardware, and bring up the appliance console.
Manage Cluster InfrastructureIndex the Local UI tasks for day-two cluster infrastructure operations.
Upgrade the PlatformUpload a newer content bundle from Artifact Studio and apply Update in Local UI.
Upload a ModelUpload a model recipe, then download the model weights on a jumpbox and upload them to the appliance.
Deploy a ModelDeploy an LLM, choose which nodes run it, and verify it is serving.
Share a GPU Between ModelsDeploy a model that shares a GPU with a group, and change a running model's GPU memory share.
Replace a ModelRemove a model from a node, then deploy a newer version or a different model.
Bring Your Own ModelAuthor metadata for a model that is not certified, then upload and deploy it.
Configure Semantic RoutingTurn the semantic router and its guard checks on or off, set routing for a policy and a client, and record decisions.
Set the Thinking Directive for a TierChoose off, on, or an effort level per tier on the Tier Map.
Enable Vision PreprocessingDeploy a vision model and turn on image-to-text preprocessing for a text-only model.
Create a WorkspaceGive a team its own workspace, and choose who can act in it.
Manage Workspace MembersAdd, change, and remove the members of a workspace.
Manage UsersAdd, change, deactivate, and delete users, and set their passwords.
Manage GroupsAdd, change, and delete groups.
Create a ClientCreate a client and issue its first API token.
Generate an API TokenCreate an API token that clients use to authenticate to the appliance.
Set and Manage Client QuotasSet, edit, raise, and remove a client's request, token, and cost limits.
Manage a Client's Model AccessRoute a client to models and allow it to reach external models.
Register an External Inference EndpointRegister an OpenAI-compatible host under Integrations, authorize a policy, and route to its models.
View Token UsageFind token usage by model and by client, and open the metrics dashboards.
View Client UsageView quota utilization, historical consumption, and per-token usage.
Revoke or Delete a ClientFind expired keys, revoke a token, or delete a client.
Use Claude CodeConnect Claude Code to the appliance so a local model serves each request.
Use CursorConnect Cursor's Ask mode to the appliance through a GPT model the appliance serves.
Use OpenAI CodexConnect the OpenAI Codex CLI to the appliance with a custom model provider.
Use OpenCodeConnect the OpenCode terminal agent to the appliance through a custom provider.