| commit | 72e0d3c9468ef3659352efbbd8a2571785fd6a22 | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scotttodd@google.com> | Tue Nov 29 13:35:55 2022 -0800 |
| committer | GitHub <noreply@github.com> | Tue Nov 29 21:35:55 2022 +0000 |
| tree | 4c67814be23842008463c5b005b5a809a44756b1 | |
| parent | b79ca72c9b61ab87cf9a9405891c68cd3fe049bc [diff] |
[WebGPU] Add compilation tests for xla_ops/ and tosa_ops/ (again). (#11327) This reverts https://github.com/iree-org/iree/pull/10918 to roll forward https://github.com/iree-org/iree/pull/10909, adding a hack to skip WebGPU testdata compilation when cross compiling. The right way to add this test coverage is likely either * Adding a new test macro that just tests compilation without even considering runtime/execution * Adding the `IREE_HAL_DRIVER_WEBGPU` option and running tests with it (this won't really work until I have more tests working, and the tools are updated to somehow handle async readback... so I'm not hopeful about this approach for at least several months)
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.