pytorch/ao
ao
PyTorch native quantization and sparsity for training and inference
Builder
pytorch
pytorch • individual
Stars
2,756
Using upstream star count
Forks
472
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Nov 3, 2023
Project creation date
README Summary
This repository provides PyTorch-native implementations of quantization and sparsity techniques for both training and inference of neural networks. It offers optimized kernels and algorithms to reduce model size and improve inference speed while maintaining accuracy.
AI Dev Skills
Unmapped
Neural Network QuantizationModel SparsityPyTorch OptimizationLow-bit InferenceCustom CUDA KernelsModel CompressionHardware-aware TrainingQuantization-aware TrainingPost-training QuantizationPruning Algorithms
Tags
Neural Network QuantizationModel SparsityPyTorch OptimizationLow-bit InferenceCustom CUDA KernelsModel CompressionHardware-aware TrainingQuantization-aware TrainingPost-training QuantizationPruning AlgorithmsOn-premiseLow-Precision TrainingTraining AccelerationInference AccelerationOn-device AICloud APIAny PyTorch-compatible data typesPyTorch Deep LearningInference Speed OptimizationEdge ComputingModel QuantizationNeural Network SparsityHardware-Aware OptimizationModel Size ReductionSelf-hostedEdge Device DeploymentEdge/MobileEfficient AIMemory Usage MinimizationModel OptimizationProduction Model OptimizationPython
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 22 days ago
7 Days
0
30 Days
0
90 Days
0
Quality
beta- Quality
- high
- Maturity
- beta
Categories
Inference & ServingPrimaryEdge & Mobile AIOther AI / MLFoundation ModelsModel Training
PM Skills
Scale & Reliability
Languages
Python100.0%
Timeline
- Project created
- Nov 3, 2023
- Forked
- Mar 22, 2026
- Your last push
- 22 days ago
- Upstream last push
- 6 days ago
- Tracked since
- Mar 22, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…