EnzymeAD/Enzyme

High-performance automatic differentiation of LLVM and MLIR.

66
/ 100
Established

Enzyme is a specialized tool for developers working with LLVM and MLIR frameworks who need to compute derivatives (gradients) of their code. It takes your existing C/C++ or other compiled code and automatically transforms it to produce highly efficient gradient computations. This is particularly useful for optimizing numerical algorithms and machine learning models, where accurately and quickly calculating how a function changes with respect to its inputs is critical.

1,558 stars. Actively maintained with 28 commits in the last 30 days.

Use this if you are a high-performance computing or machine learning developer needing to automatically differentiate functions within LLVM or MLIR to optimize performance, especially on GPUs.

Not ideal if you are not a developer working with LLVM or MLIR, or if you only need symbolic differentiation for simple mathematical expressions.

compiler-development high-performance-computing scientific-computing numerical-optimization machine-learning-engineering
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,558

Forks

154

Language

LLVM

License

Last pushed

Mar 13, 2026

Commits (30d)

28

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EnzymeAD/Enzyme"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.