Dashboard

Blog

Community

Status

Pricing

Cerebrium

Examples

Migrations

API Reference

Sign Up

Contact Us

List all hardware options

Cerebrium is a serverless GPU infrastructure provider. We want to help you run machine learning models in the cloud efficiently and at scale.

Introduction

Cerebrium is our Python framework that meets you where you work - whether it be in Notebooks or .py files we want you to feel comfortable and be environment agnostic.

Installation

Get up and running with your first deployed model on Cerebrium

Quickstart

Using config files to configure Cortex deployments easily and quickly

Initial Setup

Using Config Files

Specify your versions, dependencies and packages to use

Customizing the Cortex Runtime

Access third-party platforms using secure credentials encrypted on Cerebrium

Using Secrets

Tips and tricks for multi-GPU inferencing.

Multi-GPU Inferencing

Based on traffic and implementation you might want to keep instances running

Keep models warm

Using Custom Runtimes (Preview)

Persistent Volumes

Integrate Cerebrium into your CI/CD workflow for automated deployments

CI/CD Pipelines

OpenAI Compatible Endpoints

Rest API

Streaming Endpoints

Websocket Endpoints

Execute calls to a Cerebrium app to be run asynchroously

Asynchronous Execution (Preview)

Webhook Forwarding (Preview)

Integrate Cerebrium with Vercel to build AI applications

Vercel Integration

Decrease the time it takes to load your model from storage into GPU

Decrease Model Loading Time

Cerebrium provides prebuilt models that you can deploy to an API seamlessly

Deploying Prebuilt Models

Cerebrium follows security best practices

Security & Data Privacy

Reliability and Scalability

A list of hardware that is available on Cerebrium's platform.

Available Hardware

How to calculate the cost of your deployment on Cerebrium

Calculating compute cost

Some guidelines to boost the speed of your deployments and cold starts.

Do's and Don'ts for Faster Deployments

Explore our collection of implementation examples and tutorials

Featured Examples

Mistral 7B with vLLM

Create a OpenAI compatible endpoint using the vLLM framework

OpenAI compatible vLLM endpoint

Stream outputs live from Falcon 7B using SSE

Streaming LLM Output

Deploy an executive assistant using Langsmith and Langchain

Langchain and Langsmith

Using Distill Whisper to transcribe an audio file

Transcribe 1 hour podcast

Integrate a real-time AI voice agent with Twilio

Twilio Voice Agent

Real-time Voice AI Agent

ComfyUI application at Scale

Generate high quality images using SDXL with refiner

Generate Images using SDXL

Using FastAPI, Gradio and Cerebrium to deploy an LLM chat interface

Gradio Chat Interface

Deploy a Model from Replicate on Cerebrium

Migrating from Replicate

Deploy a Model from Hugging Face on Cerebrium

Migrating from Hugging Face

List all projects for a user

Get a project by ID

List project API keys

Get v2projects apps

Kick off app creation

Get an app by ID

Delete an app by ID

Update an app by ID

Creates a k8s job that makes an async request

List all builds for an app

Get a build by ID

Cancel a build by ID

Download a build by ID

List all logs for a build

Rebuild a build by ID

List all recent containers for an app

Get dashboard metrics for an app

Get logs for an app

List all runs for an app

Get a run by ID

Lists the most recent project containers

Get project cost per app

List all secrets for a project

Updates project secrets

Lists all volumes for a project

Complete a multipart upload for a file in a volume for a Project

Initialize a multipart upload for a file in a volume for a Project

Download a specific file for a Project

List files in a volume. `cerebrium ls` command

Resizes a PVC

Delete a file in a volume for a Project. `cerebrium rm xxx` command