Misby

ArchProbe

A profiler to disclose and quantify hardware features on GPUs.

face_recognition

The world's simplest facial recognition api for Python and the command line

FacenetAtt

llfio

P1031 low level file i/o and filesystem library for the C++ standard

MnasNet-paddle

nnPerfwins

perfetto

Performance instrumentation and tracing for Android, Linux and Chrome (read-only mirror of https://android.googlesource.com/platform/external/perfetto/)

pti-gpu

Profiling Tools Interfaces for GPU (PTI for GPU) is a set of Getting Started Documentation and Tools Library to start performance analysis on Intel(R) Processor Graphics easily

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

tiny-training

On-Device Training Under 256KB Memory [NeurIPS'22]

TinyNeuralNetwork

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

tpu

Reference models and tools for Cloud TPUs.

vision

Datasets, Transforms and Models specific to Computer Vision

coder-kung-fu

开发内功修炼

CoDL

Edge-AI-Paper-List

examples

TensorFlow examples

GPy

Gaussian processes framework in python

llama2.c

Inference Llama 2 in one file of pure C

LLMSpeculativeSampling

Fast inference from large lauguage models via speculative decoding

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

MiniGPT-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Model_Sandbox_imgclsmob

Sandbox for training deep learning networks

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

once-for-all

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

pytorch-distributed

A quickstart and benchmark for pytorch distributed training.

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 per

transformers-android-demo

📲 Transformers android examples (Tensorflow Lite & Pytorch Mobile)