alibaba / TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
☆734Updated this week
Related projects: ⓘ
- Model Quantization Benchmark☆752Updated 3 months ago
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,511Updated 5 months ago
- A simple network quantization demo using pytorch from scratch.☆497Updated last year
- A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.☆1,284Updated 2 months ago
- A parser, editor and profiler tool for ONNX models.☆379Updated 3 weeks ago
- PyTorch Neural Network eXchange☆490Updated this week
- Simple samples for TensorRT programming☆1,477Updated 2 weeks ago
- MegCC是一 个运行时超轻量,高效,移植简单的深度学习模型编译器☆466Updated last month
- ☆972Updated 6 months ago
- ☆295Updated 9 months ago
- A primitive library for neural network☆1,268Updated last month
- ppl.cv is a high-performance image processing library of openPPL supporting various platforms.☆488Updated 3 months ago
- Actively maintained ONNX Optimizer☆634Updated 6 months ago
- TensorRT Plugin Autogen Tool☆365Updated last year
- Bolt is a deep learning library with high performance and heterogeneous flexibility.☆909Updated last month
- nndeploy是一款模型端到端部署框架。以多端推理以及基于有向无环图模型部署为基础,致力为用户提供跨平台、简单易用、高性能的模型部署体验。☆600Updated this week
- micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantiz…☆2,212Updated 2 years ago
- A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are co…☆1,808Updated 4 months ago
- A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.☆333Updated last month
- EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activatio…☆389Updated last year
- Deploy your model with TensorRT quickly.☆756Updated 9 months ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆796Updated 3 weeks ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆952Updated this week
- Everything in Torch Fx☆335Updated 3 months ago
- 针对pytorch模型的自动化模型结构分析和修改工具集,包含自动分析模型结构的模型压缩算法库☆234Updated last year
- Machine learning compiler based on MLIR for Sophgo TPU.☆576Updated last month
- Neural Network Compression Framework for enhanced OpenVINO™ inference☆906Updated this week
- On-Device Training Under 256KB Memory [NeurIPS'22]☆426Updated 5 months ago
- row-major matmul optimization☆584Updated last year
- [IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer☆301Updated last year