Summary

Important

Many decoder language models can now be automatically loaded using the Transformers backend without having to implement them in vLLM. See if vllm serve <model> works first!

vLLM models are specialized PyTorch models that take advantage of various features to optimize their performance.

The complexity of integrating a model into vLLM depends heavily on the model's architecture. The process is considerably straightforward if the model shares a similar architecture with an existing model in vLLM. However, this can be more complex for models that include new operators (e.g., a new attention mechanism).

Read through these pages for a step-by-step guide:

• Basic Model
• Registering a Model
• Unit Testing
• Multi-Modal Support

Tip

If you are encountering issues while integrating your model into vLLM, feel free to open a GitHub issue or ask on our developer slack. We will be happy to help you out!