Google Git
Sign in
opensecura / 3p / openxla / iree / b3cd60a12f8f1c593a900b61d407eff138c443e5
commitb3cd60a12f8f1c593a900b61d407eff138c443e5[log] [tgz]
authorScott Todd <scotttodd@google.com>Thu Oct 12 09:40:30 2023 -0700
committerGitHub <noreply@github.com>Thu Oct 12 09:40:30 2023 -0700
tree3ed2dd5a7e2f39fc401c7e393d9bfee04e8b1ea5
parentf782069ecde3774553c0c15e1b953fea40b4a7c2 [diff]
Add pytorch_jit sample Colab notebook using SHARK-Turbine.  (#15146)

Progress on https://github.com/openxla/iree/issues/15117

This notebook shows how to use
[SHARK-Turbine](https://github.com/nod-ai/SHARK-Turbine) for eager
execution within a PyTorch session using IREE and
[torch-mlir](https://github.com/llvm/torch-mlir) under the covers. I'm
starting simple to get the concepts across, with minimal API usage and a
tiny `nn.Module` sourced from
https://pytorch.org/docs/stable/notes/modules.html. My expectation is
that this notebook will evolve alongside other notebooks (e.g.
`pytorch_aot.ipynb`), documentation
(https://github.com/openxla/iree/issues/15114), and the SHARK-Turbine
project itself.

Preview URL for review:
https://colab.research.google.com/github/openxla/iree/blob/scotttodd-pytorch-samples-1/samples/colab/pytorch_jit.ipynb

skip-ci: no-op
3 files changed
tree: 3ed2dd5a7e2f39fc401c7e393d9bfee04e8b1ea5
  1. .devcontainer/
  2. .github/
  3. build_tools/
  4. compiler/
  5. docs/
  6. experimental/
  7. integrations/
  8. lib/
  9. llvm-external-projects/
  10. runtime/
  11. samples/
  12. tests/
  13. third_party/
  14. tools/
  15. .bazel_to_cmake.cfg.py
  16. .bazelignore
  17. .bazelrc
  18. .bazelversion
  19. .clang-format
  20. .dockerignore
  21. .git-blame-ignore-revs
  22. .gitignore
  23. .gitmodules
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. README.md
  33. WORKSPACE
README.md

IREE: Intermediate Representation Execution Environment

IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler and runtime that lowers Machine Learning (ML) models to a unified IR that scales up to meet the needs of the datacenter and down to satisfy the constraints and special considerations of mobile and edge deployments.

See our website for project details, user guides, and instructions on building from source.

CI Status

Project Status

IREE is still in its early phase. We have settled down on the overarching infrastructure and are actively improving various software components as well as project logistics. It is still quite far from ready for everyday use and is made available without any support at the moment. With that said, we welcome any kind of feedback on any communication channels!

Communication Channels

Related Project Channels

  • MLIR topic within LLVM Discourse: IREE is enabled by and heavily relies on MLIR. IREE sometimes is referred to in certain MLIR discussions. Useful if you are also interested in MLIR evolution.

Architecture Overview

IREE Architecture IREE Architecture

See our website for more information.

Presentations and Talks

License

IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.