neuralmagic/deepsparse
A sparsity-aware deep learning inference runtime that runs ONNX models on CPUs with optimized performance through pruning and quantization.
Not currently ranked — collecting fresh signals.
star history
DeepSparse is a CPU inference runtime designed to execute deep learning models efficiently by leveraging sparsity techniques. It supports models from ONNX format across computer vision, NLP, and LLM domains. The runtime applies model compression methods including pruning and quantization to reduce computational overhead while maintaining accuracy, enabling faster inference on standard CPU hardware without specialized accelerators.
Frequently asked
- What is neuralmagic/deepsparse?
- A sparsity-aware deep learning inference runtime that runs ONNX models on CPUs with optimized performance through pruning and quantization.
- Is deepsparse open source?
- Yes — neuralmagic/deepsparse is an open-source project tracked on heatdrop.
- What language is deepsparse written in?
- neuralmagic/deepsparse is primarily written in Python.
- How popular is deepsparse?
- neuralmagic/deepsparse has 3.2k stars on GitHub.
- Where can I find deepsparse?
- neuralmagic/deepsparse is on GitHub at https://github.com/neuralmagic/deepsparse.