ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
☆199Dec 22, 2022Updated 3 years ago
Alternatives and similar repositories for actnn
Users that are interested in actnn are comparing it to the libraries listed below
Sorting:
- ☆43Nov 1, 2022Updated 3 years ago
- code for the paper "A Statistical Framework for Low-bitwidth Training of Deep Neural Networks"☆29Oct 31, 2020Updated 5 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆98Jun 10, 2021Updated 4 years ago
- Codes for Accepted Paper : "MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization" in NeurIPS 2019☆54May 8, 2020Updated 5 years ago
- MONeT framework for reducing memory consumption of DNN training☆174May 4, 2021Updated 4 years ago
- ☆57Dec 8, 2020Updated 5 years ago
- [ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binar…☆56Mar 4, 2024Updated last year
- ☆42Sep 8, 2023Updated 2 years ago
- ☆43Jan 30, 2024Updated 2 years ago
- source code of the paper: Robust Quantization: One Model to Rule Them All☆41Mar 24, 2023Updated 2 years ago
- ReActNet: Towards Precise Binary NeuralNetwork with Generalized Activation Functions. In ECCV 2020.☆263Nov 11, 2021Updated 4 years ago
- Binary neural networks developed by Huawei Noah's Ark Lab☆29Feb 19, 2021Updated 5 years ago
- [ICML 2022] ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks☆15May 18, 2022Updated 3 years ago
- Collections of model quantization algorithms. Any issues, please contact Peng Chen (blueardour@gmail.com)☆73Oct 7, 2021Updated 4 years ago
- ☆23Oct 7, 2021Updated 4 years ago
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆125Jun 23, 2022Updated 3 years ago
- [ICML'21 Oral] I-BERT: Integer-only BERT Quantization☆265Jan 29, 2023Updated 3 years ago
- Post-training sparsity-aware quantization☆34Feb 26, 2023Updated 3 years ago
- Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.☆453May 15, 2023Updated 2 years ago
- An external memory allocator example for PyTorch.☆16Aug 10, 2025Updated 6 months ago
- Simple Training and Deployment of Fast End-to-End Binary Networks☆160Feb 1, 2022Updated 4 years ago
- Boost hardware utilization for ML training workloads via Inter-model Horizontal Fusion☆32May 15, 2024Updated last year
- Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks☆68Nov 4, 2021Updated 4 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆1,006Sep 19, 2024Updated last year
- The code for our paper "Neural Architecture Search as Program Transformation Exploration"☆16Apr 28, 2021Updated 4 years ago
- Network Pruning That Matters: A Case Study on Retraining Variants (ICLR 2021)☆17Sep 19, 2021Updated 4 years ago
- BitSplit Post-trining Quantization☆50Dec 20, 2021Updated 4 years ago
- ☆48Jul 28, 2020Updated 5 years ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆283Dec 11, 2024Updated last year
- Low Precision Arithmetic Simulation in PyTorch☆292May 20, 2024Updated last year
- Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.☆138Apr 28, 2022Updated 3 years ago
- Deadline-based hyperparameter tuning on RayTune.☆32Jan 16, 2020Updated 6 years ago
- [TMLR] Official PyTorch implementation of paper "Efficient Quantization-aware Training with Adaptive Coreset Selection"☆37Aug 20, 2024Updated last year
- Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616☆133Jul 6, 2023Updated 2 years ago
- ☆213Nov 23, 2018Updated 7 years ago
- [CVPR 2020] This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for a…☆181Mar 14, 2020Updated 5 years ago
- This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".☆120Dec 12, 2021Updated 4 years ago
- Codes for AAAI2019 paper: Deep Neural Network Quantization via Layer-Wise Optimization using Limited Training Data☆41Jan 22, 2019Updated 7 years ago
- [ECCV 2022] SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning☆20Jul 7, 2022Updated 3 years ago