jackyh Goto Github PK

autotvm_tutorial

autoTVM神经网络推理代码优化搜索演示，基于tvm编译开源模型centerface，并使用autoTVM搜索最优推理代码，　最终部署编译为c++代码，演示平台是cuda，可以是其他平台，例如树莓派，安卓手机，苹果手机．Thi is a demonstration of how to use autoTVM to search and optimize a neural network inference code. the main process of this program is , firstly use tvm to compile opensource model centerface , then use autotvm to auto search the best inference code for the compiled model

bert

TensorFlow code and pre-trained models for BERT

caffe2

Caffe2 is a lightweight, modular, and scalable deep learning framework.

cltune

CLTune: An automatic OpenCL & CUDA kernel tuner

conv

cpp_study

follow me to study modern c++

cuda-programming

Sample codes for my CUDA programming book

cuda_pi_montecarlo

CUDA code for Monte Carlo estimation of Pi (see https://www.geeksforgeeks.org/estimating-value-pi-using-monte-carlo/)

cudabert

A Fast Muti-processing BERT-Inference System

deepbench

Benchmarking Deep Learning operations on different hardware

deeplearning4j

Model import deployment framework for retraining models (pytorch, tensorflow,keras) deploying in JVM Micro service environments, mobile devices, iot, and Apache Spark

deeplearningexamples

Deep Learning Examples

devops

阿里云容器服务持续交付

dgl-ke

High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.

dingdong-grabber

叮咚多策略抢菜/买菜，亲测有效

efficientnet-pytorch

A PyTorch implementation of EfficientNet and EfficientNetV2 (coming soon!)

espresso

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

ganglia-web

Ganglia Web Frontend

generativeaiexamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

gpushare-device-plugin

GPU Sharing Device Plugin for Kubernetes Cluster

gpushare-scheduler-extender

GPU Sharing Scheduler for Kubernetes Cluster

implicit_gemm_convolution

ingress-nginx

NGINX Ingress Controller for Kubernetes

javacpp-presets

The missing Java distribution of native C++ libraries

lightseq

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

max-pool-cuda

Implemented the max pool filter in CUDA using the in built library and using shared memory

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

moby

Moby Project - a collaborative project for the container ecosystem to assemble container-based systems

mongo

The Mongo Database

monitor-core

Ganglia Monitoring core