DeepCache
Feature reuse accelerator
A novel paradigm to accelerate diffusion models by reusing and updating high-level features in a cheap way
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
802 stars
15 watching
37 forks
Language: Python
last commit: 5 months ago diffusion-modelsefficient-inferencemodel-compressionstable-diffusiontraining-free
Related projects:
| Repository | Description | Stars |
|---|---|---|
 deepseek-ai/deepseek-moe | A large language model with improved efficiency and performance compared to similar models | 1,006 |
 vonfeng/deepmove | A PyTorch-based implementation of a predictive model for human mobility patterns using attention mechanisms and recurrent neural networks. | 144 |
 kefirski/pytorch_rvae | A deep learning implementation of a recurrent variational autoencoder for generating sequential data. | 357 |
 lge-arc-advancedai/auptimizer | Automates model building and deployment process by optimizing hyperparameters and compressing models for edge computing. | 200 |
 dome272/wuerstchen | A framework that enables efficient training of text-to-image models by compressing the computationally expensive stage into a latent space | 528 |
 deepset-ai/farm | An open-source framework for adapting representation models to various tasks and industries | 1,741 |
 diffusionkinetics/open | A monorepo of Haskell projects focused on data science and machine learning | 115 |
 ecmwfcode4earth/deepr | Project aimed at downscaling global climate data to higher resolutions using deep learning techniques. | 22 |
 baguasys/bagua | A framework for accelerating PyTorch deep learning training | 877 |
 rentruewang/koila | A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution | 1,821 |
 leopiney/tensor-safe | A Haskell framework for defining and compiling valid deep learning models to external frameworks like TensorFlow JS or Keras. | 101 |
 maxpumperla/elephas | Enables distributed deep learning with Keras and Spark for scalable model training | 1,574 |
 huaifeng1993/dfanet | An implementation of a deep learning model for real-time semantic segmentation | 254 |
| deepseek-ai/deepseek-vl | A multimodal AI model that enables real-world vision-language understanding applications | 2,077 |
 autodistill/autodistill | Automatically trains models from large foundation models to perform specific tasks with minimal human intervention. | 1,997 |