Define New Model Architectures

This page guides you how to add a new model architecture in MLC.

This notebook (runnable in Colab) should contain all necessary information to add a model in MLC LLM:

In the notebook, we leverage tvm.nn.module to define a model in MLC LLM. We also use JIT (just-in-time compilation) to debug the implementation.

You can also refer to the PRs below on specific examples of adding a model architecture in MLC LLM:


When adding a model variant that has its architecture already supported in mlc-llm , you only need to convert weights (e.g. adding CodeLlama when MLC supports llama-2; adding OpenHermes Mistral when MLC supports mistral). On the other hand, a new model architecture (or inference logic) requires more work (following the tutorial above).