Stars
Productive, portable, and performant GPU programming in Python.
C++ Requests: Curl for People, a spiritual port of Python Requests.
Piccolo (formerly Pilot) – mini game engine for games104
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
Stable Diffusion in NCNN with c++, supported txt2img and img2img
[ICCV2019 Oral] Photo-Realistic Facial Details Synthesis from Single Image
code for the rgbd-slam tutorial written in cnblogs
A High Performance Multithread Network Library
A framework for building (and incrementally growing) graph-based data structures used in hierarchical or DAG-structured clustering and nearest neighbor search