Skip to content

Backward compatible ML compute opset inspired by HLO/MHLO

License

Notifications You must be signed in to change notification settings

subhankarshah/stablehlo

 
 

Repository files navigation

StableHLO

StableHLO is an operation set that expresses ML computations. It has been originally bootstrapped from the MHLO dialect and enhances it with additional functionality, including serialization and versioning.

StableHLO is a portability layer between ML frameworks and ML compilers. We are aiming for adoption by a wide variety of ML frameworks including TensorFlow, JAX and PyTorch, as well as ML compilers including XLA and IREE.

Development

We're using GitHub issues / pull requests to organize development and GitHub discussions to have longer discussions. We also have a #stablehlo channel on the OpenXLA Discord server.

Community

With StableHLO, our goal is to create a community to build an amazing portability layer between ML frameworks and ML compilers. Let's work together on figuring out the appropriate governance to make this happen.

Roadmap

  • Workstream #1: Stable version of HLO/MHLO, including the spec, the corresponding dialect with high-quality implementations of prettyprinting, verification and type inference, and the interpeter. ETA: H2 2022.
  • Workstream #2: Evolution beyond what's currently in HLO/MHLO. Ongoing work on dynamism, sparsity, quantization and extensibility. ETA: H2 2022.
  • Workstream #3: Support for ML frameworks (TensorFlow, JAX, PyTorch) and ML compilers (XLA and IREE). ETA: H2 2022.

About

Backward compatible ML compute opset inspired by HLO/MHLO

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • MLIR 54.2%
  • C++ 41.1%
  • CMake 1.6%
  • C 1.5%
  • Other 1.6%