| commit | 890ae99e22247268fe2f5059fc441e669836e5c6 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Wed Mar 06 10:04:40 2024 -0800 |
| committer | GitHub <noreply@github.com> | Wed Mar 06 18:04:40 2024 +0000 |
| tree | f5a72f1e6c09dac7184a40e6e53f09b3ddd44149 | |
| parent | f34e534a16f9cfe328f0a513ef474fd44af29a30 [diff] |
Making the ElideAsyncCopiesPass support stream.async.slice. (#16667) This is only looking for some very specific patterns that we can (mostly) verify are safe. This can definitely be improved and widened to more cases but this is better than the nothing we do today for slice ops. It does have some gotchas around potentially increasing lifetime of source tensors but we don't have a good way of measuring that today so 🤷. Fixes #16647.
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.