| commit | c397258f87007840b8b66e66789400a9daef1c68 | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scotttodd@google.com> | Fri Oct 13 15:18:33 2023 -0700 |
| committer | GitHub <noreply@github.com> | Fri Oct 13 15:18:33 2023 -0700 |
| tree | fd19aa9fab6ccd27a9c22e3af102d9421ba6f719 | |
| parent | 3f001b695cc6d271da02d97aa2b2641bc7baf3b4 [diff] |
Add pytorch_aot_simple sample Colab notebook using SHARK-Turbine. (#15166) Progress on https://github.com/openxla/iree/issues/15117 From [SHARK-Turbine](https://github.com/nod-ai/SHARK-Turbine)'s README: > *AOT Export*: For compiling one or more `nn.Module`s to compiled, deployment ready artifacts. This operates via both a [simple one-shot export API](https://github.com/nod-ai/SHARK-Turbine/blob/main/python/shark_turbine/aot/exporter.py) for simple models and an underlying [advanced API](https://github.com/nod-ai/SHARK-Turbine/blob/main/python/shark_turbine/aot/compiled_module.py) for complicated models and accessing the full features of the runtime. This notebook shows how to use the "simple one-shot export API", with a branch between in-session compilation using `export_output.compile()` and export to native tools using `export_output.save_mlir()`. Some portion of this notebook may be included as a code sample for https://github.com/openxla/iree/issues/15114. Preview URL for review: https://colab.research.google.com/github/scotttodd/iree/blob/pytorch-samples-2/samples/colab/pytorch_aot_simple.ipynb skip-ci: no-op
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.
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!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.