Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Official code for "Parser-Free Virtual Try-on via Distilling Appearance Flows", CVPR 2021.

High-speed Large Language Model Serving for Local Deployment

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

An simple and effective segmentation framework

A Mask R-CNN Keras implementation with Modanet annotations on the Paperdoll dataset

BDD100k drivable area

vue源码逐行注释分析+40多m的vue源码程序流程图思维导图(vue source code line by line annotation analysis +40 + m vue source code process flow chart mind map)

Large single page application with 45 pages built on vue2 + vuex. 基于 vue2 + vuex 构建一个具有 45 个页面的大型单页面应用

Phalcon + Swoole

Code for CVPR2016 and TIP papers about Object Skeleton Detection with Fully Convolutional Neural Networks.

php html parser，类似与PHP Simple HTML DOM Parser，但是比它快好几倍