erectbranch/MIT-Efficient-AI

TinyML and Efficient Deep Learning Computing | MIT 6.S965/6.5940

Size: 73 MB - Last synced at: 29 minutes ago - Pushed at: about 2 hours ago - Stars: 9 - Forks: 3

HanzhiZhang-Ulrica/DAM

Dynamic Attention Mask (DAM) generate adaptive sparse attention masks per layer and head for Transformer models, enabling long-context inference with lower compute and memory overhead without fine-tuning.

Language: Python - Size: 9.77 KB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 0 - Forks: 0

jeho-lee/Awesome-On-Device-AI-Systems

Size: 26.4 KB - Last synced at: 25 days ago - Pushed at: 26 days ago - Stars: 43 - Forks: 1

BaiTheBest/SparseLLM

Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)

Language: Python - Size: 145 KB - Last synced at: 16 days ago - Pushed at: 3 months ago - Stars: 61 - Forks: 9

sujin-1013/task-aware-DMO

Task-Aware Dynamic Model Optimization for Multi-Task Learning (IEEE Access 2023)

Size: 1.47 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

Shikha-code36/early-exit-cnn

A deep learning framework that implements Early Exit strategies in Convolutional Neural Networks (CNNs) using Deep Q-Learning (DQN). This project enhances computational efficiency by dynamically determining the optimal exit point in a neural network for image classification tasks on CIFAR-10.

Language: Jupyter Notebook - Size: 179 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 1 - Forks: 0