Qing Wang's repositories
AISystem
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
DALI
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
eigen
Eigen is a C++ template library for linear algebra: matrices, vectors, numerical solvers, and related algorithms.
fastapi-users
Ready-to-use and customizable users management for FastAPI
gym
A toolkit for developing and comparing reinforcement learning algorithms.
hass-xiaomi-miot
Automatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. 小米米家智能家居设备接入Hass集成
inke
📖 A WYSIWYG notebook with AI assisted writing and real-time collaboration. Support self hosting. 一个所见即所得的Markdown笔记本,支持AI辅助写作和多人协作,支持自部署,使用IndexedDB存储笔记。
medup
Medup is a markdown parser and reader developed in Rust, including library and web service. 💖
MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
mobius
Mobius is an AI infrastructure platform for distributed online learning, including online sample processing, training and serving.
myhack-torch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
mylandingpage
A react wonderful landingpage template
onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
OpenLLaMA2
DeepSpeed+Ray based LLaMA2 SFT/RLHF training framework
PyQt-Fluent-Widgets
A fluent design widgets library based on Qt/PyQt/PySide. Make Qt Great Again.
pytorch-xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)
RAG-Theory-and-Practice
Introduce the theory and practice about RAG
shotcut
cross-platform (Qt), open-source (GPLv3) video editor
so-large-lm
大模型理论基础
T-Eval
[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step
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.
tldraw
a very good whiteboard
vmail
📫 An open source temporary email tool. 只需一个域名部署临时邮箱,支持收发邮件,多域名邮箱配置,密码找回。
xla
A machine learning compiler for GPUs, CPUs, and ML accelerators