mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
503 B
503 B
(add-model)=
Adding a Model
This document describes how to add a model in TensorRT-LLM.
TensorRT-LLM provides:
- Low-level functions, for example,
concat,add, andsum. - Basic layers, such as,
LinearandLayerNorm. - High-level layers, such as,
MLPandAttention.
Steps
- Create a model directory in
tensorrt_llm/tensorrt_llm/models, for examplebloom. - Write a
model.pywith TensorRT-LLM low level functions and basic layers. It's optional to use high level layers.