28 docs tagged with "how-to"

Step-by-step guidance for platform operators on how to bring a model that is not in the certified catalog onto a PaletteAI Inference Launchpad appliance by authoring its metadata file, then uploading and deploying it.

Step-by-step guidance for platform administrators on how to turn the semantic router and its guard checks on or off, set routing rules for a workspace's policy and for a client, set a client's Complexity threshold, and record routing decisions on a PaletteAI Inference Launchpad appliance.

Step-by-step guidance for platform administrators on how to create a client on a PaletteAI Inference Launchpad appliance by stepping through the Add client wizard and issuing the client's first API token.

Create a workspace on a PaletteAI Inference Launchpad appliance, choose the policy it follows, and add the people and groups who can act in it.

Step-by-step guidance for platform operators on how to deploy an LLM model to a running PaletteAI Inference Launchpad appliance, choose which nodes run it, and verify that it is serving.

Step-by-step guidance for platform operators on how to deploy a vision model alongside a text-only model and enable multimodal preprocessing so image requests are answered on the appliance.

Step-by-step guidance on how to generate an API token in the PaletteAI Inference Launchpad console so that coding assistants and other clients can authenticate to the appliance.

Step-by-step guidance for platform operators on how to install the PaletteAI Inference Launchpad appliance from bare hardware to a running, reachable appliance console.

Step-by-step guidance for platform administrators on how to route a client to specific models and allow a client to reach external models on a PaletteAI Inference Launchpad appliance.

Index of the Local UI tasks that platform operators use to run day-two cluster infrastructure operations on a PaletteAI Inference Launchpad appliance.

Add, change, and delete groups on the Groups tab of a PaletteAI Inference Launchpad appliance.

Add, change, deactivate, and delete users, and set their passwords, on the Users tab of a PaletteAI Inference Launchpad appliance.

Add, change, and remove the people and groups who can act in a PaletteAI Inference Launchpad workspace, and the role each one holds.

Step-by-step guides for completing specific operational tasks on a running PaletteAI Inference Launchpad appliance.

Step-by-step guidance for platform administrators on how to register an OpenAI-compatible external inference endpoint under Integrations, authorize a policy to use it, and route requests to its models.

Step-by-step guidance for platform operators on how to put a newer version of a model, or a different model, on a node by removing the current model and then deploying the replacement.

Step-by-step guidance for platform administrators on how to find expired keys, revoke an API token, and delete a client on a PaletteAI Inference Launchpad appliance, and what happens to in-flight requests.

Step-by-step guidance for platform administrators on how to set, raise, edit, and remove usage quotas on a client on a PaletteAI Inference Launchpad appliance.

Step-by-step guidance for platform administrators on how to set the Thinking directive for a tier on the Tier Map of a PaletteAI Inference Launchpad appliance.

Step-by-step guidance for platform operators on how to deploy a model that shares a GPU with other models on a PaletteAI Inference Launchpad appliance, and how to change the GPU memory share of a model that already runs.

How to upgrade the PaletteAI Inference Launchpad appliance from Local UI by uploading a newer content bundle and applying the Update action.

Step-by-step guidance for platform operators on how to upload a model recipe and the model weights from a jumpbox to a PaletteAI Inference Launchpad appliance with the Palette CLI, so that the model appears in the deploy catalog.

Connect Anthropic's Claude Code coding agent to a PaletteAI Inference Launchpad appliance so that a model on the appliance serves every request.

Connect the Cursor code editor to a PaletteAI Inference Launchpad appliance so that a model on the appliance serves your requests in Cursor's Ask mode.

Connect the OpenAI Codex CLI to a PaletteAI Inference Launchpad appliance so that a model on the appliance serves every request.

Connect the OpenCode terminal coding agent to a PaletteAI Inference Launchpad appliance so that a model on the appliance serves every request.

Step-by-step guidance for platform administrators on how to view quota utilization, historical consumption, and per-token usage on a PaletteAI Inference Launchpad appliance.

Step-by-step guidance for platform administrators on how to view token usage by model and by client, find the top consumers, and open the metrics dashboards on a PaletteAI Inference Launchpad appliance.