CerebriumAI/examples

Examples for Cerebrium Serverless GPUs

What it solves

It provides a comprehensive library of practical, ready-to-use implementation examples for developers building and deploying AI applications on the Cerebrium platform. It bridges the gap between platform capabilities and real-world deployment by offering pre-configured templates for various AI modalities.

How it works

Each example is a self-contained project targeting a specific use case. Users clone the repository and use the cerebrium deploy command within the specific example folder to push the application to the Cerebrium platform. The examples cover a wide range of technical implementations, from basic model deployment to advanced inference optimizations.

Who it’s for

Machine learning engineers and AI developers who want to quickly prototype and deploy LLMs, voice agents, image generation pipelines, and other AI services without starting from scratch.

Highlights

  • Diverse AI Modalities: Includes examples for LLMs (vLLM, Falcon), Voice (Whisper, XTTS, real-time agents), and Image/Video (Stable Diffusion, ComfyUI, ControlNet).
  • Inference Optimization: Demonstrates advanced techniques like multi-GPU inference, Inferentia deployment, and faster weight loading.
  • Integration Patterns: Provides templates for Langchain QA systems, tool-calling with Langsmith, and WebSocket-based streaming.
  • Production Tooling: Examples for implementing request batching using LitServe and transformers, and deploying FastAPI or Gradio interfaces.

Related

  • Project
    Arm-Examples/ML-examples

    A collection of machine learning examples and tutorials for deploying and optimizing AI models on Arm Ethos NPUs and Cortex-based platforms.

  • Project
    qualcomm/ai-hub-apps

    A collection of sample apps and tutorials for deploying and optimizing machine learning models on Qualcomm Snapdragon devices across Android, Windows, and Ubuntu.

  • Project
    Liquid4All/cookbook

    A comprehensive collection of examples and tutorials for deploying and fine-tuning Liquid AI's open-weight Liquid Foundation Models (LFMs) on laptops, mobile, and edge devices.

  • Project
    pipecat-ai/pipecat-examples

    A collection of intermediate and advanced example applications for building voice and multimodal AI agents using the Pipecat framework.

  • Project
    OpenSQZ/MiniCPM-V-CookBook

    A comprehensive cookbook of deployment and fine-tuning recipes for the MiniCPM series of multimodal models, supporting text, vision, and audio capabilities across various hardware.