[CVPR 2023] DepShape:走向任何结构性修剪; LLM、Vision Foundation模型等。
efficient-deep-learning 开源项目推荐(90 个)
efficient-deep-learning 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 90 个仓库[TMLR 2024] 高效大型语言模型:综述
高效深度学习系统课程材料
Collection of recent methods on (deep) neural network compression and acceleration.
Code and resources on scalable and efficient Graph Neural Networks (TNNLS 2023)
📚 Collection of awesome generation acceleration resources.
[IEEE TPAMI] Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
[ECCV 2026] “ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device”的官方实现。一个紧凑的 610 万参数网络,用于零样本单目深度估计,通过从基础模型进行知识蒸馏,可在从服务器 GPU 到手机等设备上实时运行。
[NeurIPS 2023] Structural Pruning for Diffusion Models
📚 Collection of token-level model compression resources.
[TMLR 2025] Efficient Diffusion Models: A Survey
Official implementation of "EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS"
[NeurIPS2022] Official implementation of the paper 'Green Hierarchical Vision Transformer for Masked Image Modeling'.
[CVPR 2024] Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
a curated list of high-quality papers on resource-efficient LLMs 🌱
[EMNLP 2026] 📚 A curated list of Awesome Efficient dLLMs Papers with Codes
[NeurIPS 2021] Official codes for "Efficient Training of Visual Transformers with Small Datasets".
[CVPR 25] “EfficientViM:基于隐藏状态混合器的状态空间对偶性的高效视觉 Mamba”的官方实现(Pytorch)
Making DensePose fast and light (WACV 2021): mobile DensePose models on Detectron2, with checkpoints on Hugging Face
LauzHack Deep Learning Bootcamp
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/efficient-deep-learning。
- 该话题在 GitHub 上共有 90 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1 万 Star,覆盖 3 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。