hezeli123

Pinned Repositories

DeepLearningFlappyBird
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
Language:Python00
flash-attention
Fast and memory-efficient exact attention
Language:Python00
front_back_separation
The repository provides a solution to SDK API architecture. To achieve the goal of front back separation, using swig to support Java and Python and so on. This repository shows an architecture which can expand easily.
Language:C++43
Megatron-LM
Ongoing research training transformer models at scale
Language:Python00
serving
A flexible, high-performance serving system for machine learning models
Language:C++00
swig
SWIG is a software development tool that connects programs written in C and C++ with a variety of high-level programming languages.
Language:C++00
tensorflow
An Open Source Machine Learning Framework for Everyone
Language:C++00
TNN
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
Language:C++00
toft
C++ Base Library for serverside development
Language:C++00
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Language:C++8.7k 93 2k991

hezeli123's Repositories

hezeli123/front_back_separation
The repository provides a solution to SDK API architecture. To achieve the goal of front back separation, using swig to support Java and Python and so on. This repository shows an architecture which can expand easily.
Language:C++43
hezeli123/DeepLearningFlappyBird
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
Language:Python00
hezeli123/flash-attention
Fast and memory-efficient exact attention
Language:Python00
hezeli123/Megatron-LM
Ongoing research training transformer models at scale
Language:Python00
hezeli123/serving
A flexible, high-performance serving system for machine learning models
Language:C++00
hezeli123/swig
SWIG is a software development tool that connects programs written in C and C++ with a variety of high-level programming languages.
Language:C++00
hezeli123/tensorflow
An Open Source Machine Learning Framework for Everyone
Language:C++00
hezeli123/TNN
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
Language:C++00
hezeli123/toft
C++ Base Library for serverside development
Language:C++00