---
library_name: pytorch
---

![efficientvit_logo](resource/EfficientViT.png)

EfficientViT is a new family of high-resolution vision models with novel multi-scale linear attention. As such, EfficientViT delivers remarkable performance gains over previous state-of-the-art models with significant speedup on diverse hardware platforms, including mobile CPU, edge GPU, and cloud GPU.

Original paper: [EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction](https://arxiv.org/abs/2205.14756)

# EfficientViT-L2

EfficientViT is a new family of vision models for efficient high-resolution dense prediction. The core building block of EfficientViT is a new lightweight multi-scale linear attention module that achieves global receptive field and multi-scale learning with only hardware-efficient operations.

Model Configuration:
- Reference implementation: [EfficientViT-L2](https://github.com/CVHub520/efficientvit)
- Original Weight: [l2.pt](https://www.dropbox.com/scl/fi/565wb47z1f5re9jckr42t/l2.pt?rlkey=ojffxngf6iv0oiost6c2tskul&dl=0)
- Dataset: ADE20K
- Resolution: 3x512x512
- Support Cooper version:
    - Cooper SDK: [2.5.2]
    - Cooper Foundry: [2.2]

| Model | Device | Model Link |
| :-----: | :-----: | :-----: |
| EfficientViT-L2 | N1-655 | [Model_Link](https://huggingface.co/Ambarella/EfficientViT/blob/main/n1-655_efficientvit_l2.bin) |
| EfficientViT-L2 | CV72 | [Model_Link](https://huggingface.co/Ambarella/EfficientViT/blob/main/cv72_efficientvit_l2.bin) |
| EfficientViT-L2 | CV75 | [Model_Link](https://huggingface.co/Ambarella/EfficientViT/blob/main/cv75_efficientvit_l2.bin) |