Move test_tf_integrations to pkgci. (#16319) Progress on https://github.com/openxla/iree/issues/16203. I'm tempted to just finish removing these tests, but they do provide some useful coverage. We need _some_ framework tests in-tree, but they should reflect current priorities (JAX/PJRT, PyTorch, ONNX, etc.). I dropped `test_tf_integrations_gpu` because figuring out how to run that through pkgci will take more time than I want to spend (needs the GPU driver deps from Docker together with the Python packages in a venv, etc.) and I think the CPU coverage is enough for now. * This also orphans the 'frontends-nvidia' docker image, but I figure we can keep it around and remove it together with related images in a future cleanup change.
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.