Skip to content

v0.1.0
Compare
Choose a tag to compare
@github-actions github-actions released this 04 May 16:37
· 516 commits to master since this release
v0.1.0
abd2969

First release completely based on MLIR.

This release supports log-likelihood inference on the following architectures:

  • CPUs: All CPU architectures supported by LLVM. Vectorization is currently only available on X86 architectures.
  • GPUs: CUDA GPUs.

The currently supported SPFlow leave nodes are Gaussian, Categorical and Histogram.

This version also comes with a convenient Python interface to the compiler, which directly integrates with SPFlow, see the usage example in the README on how to use this interface.

The release comes with some pre-built Python wheels to facilitate installation of SPNC:

  • xspn-0.1-py3-none-any.whl: The serialization library used by the compiler (can also be used standalone, see README). This wheel is platform-agnostic.
  • spnc-0.1-py3-none-linux_x86_64.whl: The compiler itself. This version only supports inference on CPUs and should be usable on any common Linux platform.
  • spnc_gpu-0.1-py3-none-linux_x86_64.whl: The compiler itself. This version supports inference on CPUs and CUDA GPUs and should be usable on any Linux platform with CUDA 11.2 and the CUDA driver installed.

For more installation options, see the Installation Manual.

Assets 5
Loading