SparseML
Enable sparsity with a few lines of code, through open-source libraries, to boost neural network inference performance.
Large Models Are Inefficient
Many of the top models across NLP and computer vision domains are difficult and expensive to use in a real-world deployment. While they are accurate, they are computationally intensive, which can require inflexible hardware accelerators in production.Small Models Are Less Accurate
Smaller models, while faster and more efficient, deliver less accuracy on real-world data.What if you could deliver big model accuracy with small model performance?
Meet SparseML
Optimize Your Models for Inference
SparseML enables you to create inference-optimized sparse models using state-of-the-art pruning and quantization algorithms. Models trained with SparseML can then be exported to ONNX and deployed with DeepSparse for GPU-class performance on CPU hardware.
Your Model Optimization Toolkit
Accelerate Inference
Deploy models optimized by SparseML with GPU-class performance on DeepSparse.Use Common Models
Convenient integrations for optimizing PyTorch, Ultralytics, and Hugging Face models.Leverage the Latest
Adopt state-of-the-art (SOTA) compression algorithms to make inference efficient.Product Overview
SOTA Optimization Algorithms
Boost model performance with the same accuracy by introducing sparsity.
Pre-Optimized Models
Fine tune pre-sparsified versions of common models like BERT, YOLOv5, and ResNet-50 onto your datasets.
Training Pipeline Integrations
Use with your existing SOTA software like PyTorch, Ultralytics, and Hugging Face.
Standard Logging
Gain visibility around model experiment tracking through TensorBoard and Weights & Biases.
ONNX Export
Export your sparse models to ONNX format for deployment with DeepSparse.
Manageable Workflow
Get started with just a few lines of code.
Custom Modifiers
Modify any training graph and easily get to a functioning implementation.