DeepCache
by horseee
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
AI summary
Feature reuse accelerator
A novel paradigm to accelerate diffusion models by reusing and updating high-level features in a cheap way
- stars
- 818
- forks
- 39
- watching
- 15
Similar projects
Found by comparing what the projects do, not just their names.
Efficient LLM
A large language model with improved efficiency and performance compared to similar models
Human Mobility Model
A PyTorch-based implementation of a predictive model for human mobility patterns using attention mechanisms and recurrent neural networks.
RVAE
A deep learning implementation of a recurrent variational autoencoder for generating sequential data.
Model optimizer
Automates model building and deployment process by optimizing hyperparameters and compressing models for edge computing.
Image model compressor
A framework that enables efficient training of text-to-image models by compressing the computationally expensive stage into a latent space
deepset-ai/farm1.7K
Model adapter
An open-source framework for adapting representation models to various tasks and industries
Data Science Toolkit
A monorepo of Haskell projects focused on data science and machine learning
Data enhancer
Project aimed at downscaling global climate data to higher resolutions using deep learning techniques.
Deep learning accelerator
A framework for accelerating PyTorch deep learning training
Memory optimizer for deep learning models
A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution
Model compiler
A Haskell framework for defining and compiling valid deep learning models to external frameworks like TensorFlow JS or Keras.
Model trainer
Enables distributed deep learning with Keras and Spark for scalable model training
Semantic segmentation model
An implementation of a deep learning model for real-time semantic segmentation
Vision-Language Model
A multimodal AI model that enables real-world vision-language understanding applications
Model distiller
Automatically trains models from large foundation models to perform specific tasks with minimal human intervention.
