vpoul Goto Github PK

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

awesome-deep-neural-network-compression

Summary, Code for Deep Neural Network Quantization

bitsandbytes

8-bit CUDA functions for PyTorch

bolt

Bolt is a deep learning library with high performance and heterogeneous flexibility.

bolt-1

10x faster matrix and vector operations

brecq

Pytorch implementation of BRECQ, ICLR 2021

deepsparse

Inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application

finitestateentropy

New generation entropy codecs : Finite State Entropy and Huff0

gdsc-core

Contains core code used by the GDSC ImageJ Plugins and GDSC SMLM ImageJ Plugins

llm-analysis

Latency and Memory Analysis of Transformer Models for Training and Inference

mace

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

mindspore

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

mmrazor

OpenMMLab Model Compression Toolbox and Benchmark.

mnn

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

mqbench

Model Quantization Benchmark

mvision

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

neural-compressor

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

onednn

oneAPI Deep Neural Network Library (oneDNN)

paddleslim

PaddleSlim is an open-source library for deep model compression and architecture search.

py-tans

A Python Implementation of the tabled Asymmetric Numeral Systems compression method.

repdistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

retraining-free-pruning

[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

tengine

Tengine is a lite, high performance, modular inference engine for embedded device

tnn

TNN: developed by Tencent Youtu Lab and Guangying Lab, a lightweight and high-performance deep learning framework for mobile inference. 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. TNN：由腾讯优图实验室和光影实验室协同打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

vpoulhome