| commit | 2af25b5a1ac128a42a76234c5caf8ca55fc602ed | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scott.todd0@gmail.com> | Wed Jul 24 11:30:15 2024 -0700 |
| committer | GitHub <noreply@github.com> | Wed Jul 24 11:30:15 2024 -0700 |
| tree | 7f3074eac10348c1e7e3988447c35816194e2056 | |
| parent | f99df2918b28bbf2ee50e7b1a3608c822f6745e8 [diff] |
Drop `python_release_packages` CI job in favor of pkgci. (#17958) Fixes https://github.com/iree-org/iree/issues/17955. ~~This puts the "validate wheels" step right in the build job, when it could be moved to a separate job. I figure that any following jobs should be able to trust that the wheels pass basic validation, though this does add 20 seconds to the front of the pipeline.~~ ^ Nevermind, just added a new job. The way the wheels are built/uploaded/downloaded was a bit tricky to parse through and this keeps the flow compartmentalized. ci-exactly: build_packages, unit_test
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.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.