Stars
C++高性能分布式服务器框架,webserver,websocket server,自定义tcp_server（包含日志模块，配置模块，线程模块，协程模块，协程调度模块，io协程调度模块，hook模块，socket模块，bytearray序列化，http模块，TcpServer模块，Websocket模块，Https模块等, Smtp邮件模块, MySQL, SQLite3, ORM,Red…
VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization
📚 Modern C++ Tutorial: C++11/14/17/20 On the Fly | https://changkun.de/modern-cpp/
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
The nodes detached from [ComfyUI Layer Style](https://github.com/chflame163/ComfyUI_LayerStyle) are mainly those with complex requirements for dependency packages.
Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]
[ECCV 2024 Oral] PetFace: A Large-Scale Dataset and Benchmark for Animal Identification https://arxiv.org/abs/2407.13555
Z-Image workflow with predefined styles for high-quality image generation and a user-friendly experience. Includes pre-configured versions for GGUF and SAFETENSORS checkpoint formats.
A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
A framework for efficient model inference with omni-modality models
A PyTorch-native inference engine with hybrid cache acceleration and massive parallelism for DiTs.
A PyTorch native platform for training generative AI models
Official inference repo for FLUX.2 models
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)
Code release for our NeurIPS 2024 Spotlight paper "GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing"
how to optimize some algorithm in cuda.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等
Implement a Pytorch-like DL library in C++ from scratch, step by step
DeepEP: an efficient expert-parallel communication library
中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling