swift and swift-apis

These two projects are **complements**, where the Swift for TensorFlow project provides the core compiler and runtime for integrating Swift with TensorFlow, while Swift for TensorFlow Deep Learning Library offers the high-level APIs and abstractions necessary for building deep learning models within that ecosystem.

swift
46
Emerging
swift-apis
50
Established
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 20/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 24/25
Stars: 6,145
Forks: 612
Downloads: —
Commits (30d): 0
Language: Jupyter Notebook
License: Apache-2.0
Stars: 792
Forks: 135
Downloads: —
Commits (30d): 0
Language: Swift
License: Apache-2.0
Archived Stale 6m No Package No Dependents
Archived Stale 6m No Package No Dependents

About swift

tensorflow/swift

Swift for TensorFlow

Integrated language-level automatic differentiation into Swift's type system via the `Differentiable` protocol, enabling gradient computation for custom data structures beyond tensors. Developed a value-semantics deep learning API and XLA-based GPU/CPU runtime, while establishing 30+ reference models spanning computer vision, NLP, and other domains. Influenced Swift's evolution with proposals like dynamic member lookup and callable types, with spinoff projects like PythonKit and swift-jupyter extending interoperability.

About swift-apis

tensorflow/swift-apis

Swift for TensorFlow Deep Learning Library

Scores updated daily from GitHub, PyPI, and npm data. How scores work