Xtra-Computing/thundersvm

Health v2 · maintenance only

Adoption not part of the score

1621 stars · 222 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ThunderSVM is a fast SVM library that accelerates support vector machine training on GPUs (via CUDA) and multi-core CPUs. It supports all LibSVM functionalities (SVC, SVR, one-class SVM, probabilistic SVMs) with LibSVM-compatible command-line options and Python, R, Matlab, and Ruby interfaces.

Use cases

• train SVM classifiers on large datasets with GPU acceleration
• speed up libsvm workloads without changing command-line options
• fit support vector regression models faster than libsvm
• use SVMs from Python with a scikit-learn-like interface
• run one-class SVM anomaly detection on GPU
• train probabilistic SVMs quickly
• use SVMs on machines without GPUs via multi-core CPU support

When to choose

• you need SVM training that is much faster than libsvm on large datasets
• you have an NVIDIA GPU with CUDA and want drop-in LibSVM-compatible behavior
• you want SVM access from Python, R, Matlab, or Ruby

When to avoid

• you need deep learning or gradient boosting instead of SVMs (consider ThunderGBM for GBDT)
• you have no GPU and a small dataset where libsvm suffices
• you need actively developed cutting-edge features or frequent releases

Facets

library · maturity maintenance

machine-learning machine-learning data-science windows python cpp svm libsvm-compatible cuda gpu-acceleration scikit-learn-interface classification regression one-class-svm linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Xtra-Computing/thundersvm")