Zhihang Yuan

LLM-Viewer. Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

nn_tools. Neural Network Tools: Converter and Analyzer. For caffe, pytorch, draknet and so on.

PTQ4ViT. Post-Training Quantization for Vision transformers.

RPTQ4LLM. Reorder-based post-training quantization for large language model

PB-LLM. PB-LLM: Partially Binarized Large Language Models

ASVD4LLM. Activation-aware Singular Value Decomposition for Compressing Large Language Models

video_labeler. A GUI tool for conveniently label the objects in video, using the powerful object tracking.

darknet-visualizer. A visualizer of darknet nerual network's network

TorchQuantExtension. Pytorch extension for quantization with high-efficient CUDA kernels

pytorch-layerwise-OpCounter. Layer-wise Count the MACs and parameters of PyTorch model.

ModelASV. ModelASV: Analyze, Simulate and Visulize the Performance of Large Neural Network Models

shadowsocks_autoset. Automatically set the free SS account from a website for windows shadowsocks client.

MiscTritonCuda. MiscTritonCuda is a feature-rich library designed to provide miscellaneous operators and helper functions related to Triton and CUDA acceleration.

PIMAnalyzer. Tool for analyzing the details of crossbar for different applications on PIM

WechatBot. TypeScript

face_recognition-1. 使用webface人脸数据集以及DeepID网络，通过Caffe训练出模型参数，得到LFW二分类的人脸识别准确率。

MTCNN_API. Convenient API of MTCNN face or face landmark detection