capabilities.work

Change an endpoint's model, hardware or scaling

One step with Hugging Face. We can help you get access.

Get something done

Change an endpoint's model, hardware or scaling

with Hugging Face · Artificial Intelligence Management

Use Hugging Face: its Hugging Face Inference Endpoints API lets you change an endpoint's model, hardware or scaling in a single step (PUT /endpoint/{namespace}/{endpoint_name}). capabilities.work can help you get signed up and connected.

  • Can I swap the model on an existing endpoint without recreating it?
  • Is it possible to move a running endpoint to bigger hardware or change its autoscaling?
Say it to your AI assistant
  • Update endpoint {endpoint_name} in {namespace} to serve {model}.
  • Change the compute settings of {endpoint_name} under {namespace} to {compute}.
  • Switch the security type of endpoint {endpoint_name} in {namespace} to {type}.
For your developer

PUT /endpoint/{namespace}/{endpoint_name} in Hugging Face Inference Endpoints API. Full spec on APIs.io.

More you can do with Hugging Face

List Inference Endpoints in a namespaceDeploy a new Inference EndpointGet an Inference Endpoint's detailsPermanently delete an Inference EndpointPause an endpoint to stop compute costsResume a paused endpointScale an endpoint down to zero replicasRead an endpoint's runtime logsGet an endpoint's traffic and latency metricsGenerate an image with a chosen Hub modelComplete a prompt via the completions APIGenerate text in one response on TGI