Introduction to Large Language Models (LLMs) and Shared Hosting

Large Language Models (LLMs) are a type of artificial intelligence (AI) models designed to process and understand human language. They are trained on vast amounts of text data and can generate human-like responses. Shared hosting of LLMs allows multiple users to access and utilize these models, making them more accessible and cost-effective.

The Advantages of STACKIT AI Model Serving

STACKIT AI Model Serving is a fully managed hosting environment tailored for AI models, especially LLMs. Our service manages the deployment, scaling, and maintenance of AI models, allowing customers to focus on building their AI-driven applications without worrying about the complexities of model hosting, security, or infrastructure upkeep.

Ease of Use

With STACKIT AI Model Serving, you can easily use, manage, and integrate LLMs into your applications. Our service offers automatic scaling and version upgrades, ensuring that models are always operating at peak performance. The Tutorials section (and First Steps with common frameworks) offers a range of implementation examples, from simple to advanced, covering popular client frameworks.

STACKIT AI Model Serving APIs

STACKIT AI Model Serving provides two APIs to interact with our service:

  • STACKIT AI Model Serving API (Product API): This API allows you to manage your authentication tokens and get information about the shared LLMs. To get started with the Control Plane API, please refer to our Getting Started with the Product API guide.
  • Inference API (OpenAI Compatible API): This API is used to send requests to and receive responses from the hosted models. To use the inference API, you will need to authenticate yourself with an auth token. For more information, please refer to our Getting Started with Shared Models guide.

Benefits of Our Service

STACKIT AI Model Serving offers several benefits, including:

  • Freedom of choice: Our model portfolio gives you the flexibility to choose the best open source LLM for your specific use case.
  • Easy-to-Use API: Our service is designed to be simple and intuitive, making it easy to integrate open-source LLMs into your applications. We achieve this through the OpenAI compatibility of our services.
  • Many Integrations: Our inference API supports many integrations, making it easy to connect with other services and tools.

By using STACKIT AI Model Serving, you can focus on building your generative-AI-driven applications without worrying about the complexities of model hosting and management.