Update endpoint

documented

Update an Inference Endpoint (e.g., min/max replicas, repo, hardware).

PATCH /endpoints/{endpointName}Inference Endpointsno implementation yet0 runs

Input

namespace*

Namespace

my-org

endpointName*

Endpoint Name

my-endpoint

accelerator

Accelerator

cpu|gpu

instance_size

Instance Size

small|medium|large

instance_type

Instance Type

e.g. intel-icl

min_replica

Minimum Replicas

max_replica

Maximum Replicas

scale_to_zero_timeout

Scale To Zero Timeout (minutes)

repository

Model Repository

user/model

revision

Model Revision

main

task

Task

text-generation

framework

Framework

pytorch|tf

custom_image

Custom Image

JSON object for custom image

secrets

Secrets

JSON object of secrets

Calls Hugging Face as you (your API key is your account); keychains.dev holds the credentials.