xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU Clusters

Making large AI models cheaper, faster and more accessible

A high-throughput and memory-efficient inference and serving engine for LLMs

Benchmark the serving

An MLIR-Based Ideas Landing Project

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Open deep learning compiler stack for cpu, gpu and specialized accelerators

MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022

A technical report on convolution arithmetic in the context of deep learning

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

基于深度强化学习的原神自动钓鱼AI

System for AI Education Resource.

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Examples for classification, object detection, segmentation, embedding networks and more. Including Grad-C…

😎 A Collection of Awesome NCNN-based Projects

👋 Lab assignments for Introduction Course of dian.ai (Dian AI Group).

Dian团队烽火项目仓库地址

Wakatime Weekly Metrics on your Profile Readme.