xuweijia-buaa Goto Github PK

996.icu

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

allennlp

An open-source NLP research library, built on PyTorch.

alphafm

Multi-thread implementation of Factorization Machines with FTRL for binary-class classification problem.

baidu-allreduce

cpufp

A CPU tool for benchmarking the peak of floating points

cs61b

UC berkley cs61b homework and projects

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

cuda-sgemm-nicolas

cute-gemm

cutlass

CUDA Templates for Linear Algebra Subroutines

deep-learning-framework-needle

torch-like, can train cnn,lstm network etc.

deepctr-torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

deeprec

DeepRec is a recommendation engine based on TensorFlow.

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

drkbymrc

ece408

flash-attention

Fast and memory-efficient exact attention

gated-attention-reader-model

a Pytorch version of Gated Attention(GA) Reader model

go

The Go programming language

gomoduletest

gopl.io

Example programs from "The Go Programming Language"

gospark

graph-rec

Senior Capstone Project: Graph-Based Product Recommendation

graphsage

Representation learning on large graphs using stochastic graph convolutions.

hands-on-gemm

handson-ml

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.

hanxunre_as_one_baseline

joint NRE by hanxu.etc,add some changes

how_to_optimize_in_gpu-qiqizi

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

kb2e

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE