Xilinx / brevitas
Brevitas: neural network quantization in PyTorch
☆1,203Updated this week
Related projects ⓘ
Alternatives and complementary repositories for brevitas
- Dataflow compiler for QNN inference on FPGAs☆748Updated this week
- Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.☆413Updated last year
- QKeras: a quantization deep learning library for Tensorflow Keras☆541Updated 3 weeks ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆268Updated 2 years ago
- Machine learning on FPGAs using HLS☆1,287Updated this week
- Quantization of Convolutional Neural networks.☆238Updated 3 months ago
- Low Precision Arithmetic Simulation in PyTorch☆265Updated 6 months ago
- Unofficial implementation of LSQ-Net, a neural network quantization framework☆277Updated 6 months ago
- [CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision☆370Updated 3 years ago
- Model Quantization Benchmark☆765Updated 5 months ago
- Binarized Neural Network (BNN) for pytorch☆503Updated last year
- ☆394Updated 5 months ago
- Tutorial notebooks for hls4ml☆303Updated 3 weeks ago
- ☆580Updated 3 years ago
- An Open-Source Library for Training Binarized Neural Networks☆707Updated 3 months ago
- A simple network quantization demo using pytorch from scratch.☆511Updated last year
- PyTorch library to facilitate development and standardized evaluation of neural network pruning methods.☆424Updated last year
- Dataflow QNN inference accelerator examples on FPGAs☆185Updated 2 weeks ago
- [ICML'21 Oral] I-BERT: Integer-only BERT Quantization☆229Updated last year
- QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX☆127Updated 3 weeks ago
- Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.☆1,489Updated 2 months ago
- collection of works aiming at reducing model sizes or the ASIC/FPGA accelerator for machine learning☆555Updated 9 months ago
- PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.☆258Updated last year
- HLS based Deep Neural Network Accelerator Library for Xilinx Ultrascale+ MPSoCs☆323Updated 5 years ago
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,151Updated this week
- Berkeley's Spatial Array Generator☆815Updated this week
- [CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework☆274Updated 11 months ago
- Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.☆340Updated last week
- Pytorch implementation of BRECQ, ICLR 2021☆254Updated 3 years ago
- ☆337Updated last year