IITH-Compilers/IR2Vec

Implementation of IR2Vec, LLVM IR Based Scalable Program Embeddings

56
/ 100
Established

Generates distributed vector representations of programs directly from LLVM IR using an unsupervised approach, enabling machine learning applications on code without manual feature engineering. Supports both symbolic and flow-aware embedding modes at program or function granularity, with configurable vector dimensions (75, 100, 300). Available as a Python package, C++ library, or standalone binary that integrates seamlessly with LLVM's compilation pipeline across versions 8.0.1 through 20.1.0.

101 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

101

Forks

43

Language

LLVM

License

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/IITH-Compilers/IR2Vec"

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