NVIDIA DALI-based data loader integrated into your favorite DL frameworks (such as mmdetection).

Open-Sora: Democratizing Efficient Video Production for All

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

RDMA core userspace libraries and daemons

一种任务级GPU算力分时调度的高性能深度学习训练平台

ccache – a fast compiler cache

LibTorch 中文教程。

JSON for Modern C++

The official Meta Llama 3 GitHub site

CUDA integration for Python, plus shiny features

[CVPR 2024] Deformable Convolution v4

Version of TeaLeaf using CUDA

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Deformable ConvNets V2 (DCNv2) in PyTorch

Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration

Jetson Benchmark

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

Open-vocabulary Semantic Segmentation

PyTorch codes for "LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning"

SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models