Xin Yao's Projects
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP
A python implementation for 'Clustering by fast search and find of density peaks' in science 2014.
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
my leetcode solution
Ongoing research training transformer models at scale
NeMo: a toolkit for conversational AI
NeMo Megatron launcher and tools
Numpy main repository
清华大学OS公开课——课后练习
Low-Level Graph Neural Network Operators for PyG
Try some python crawlers.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Computation using data flow graphs for scalable machine learning
清华大学学生宿舍电量和热水查询及提醒Bot
PyTorch Library for Fast and Easy Distributed Graph Learning
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
Lab Codes for MOOC OS course in Tsinghua University.
Some useful utils, e.g., for tfrecords
Datasets, Transforms and Models specific to Computer Vision
Personal Page/CV