| commit | 90a022526e36861e942384d36178c92f6bdb17d9 | [log] [tgz] |
|---|---|---|
| author | Quinn Dawkins <quinn@nod-labs.com> | Thu Oct 05 09:25:09 2023 -0400 |
| committer | GitHub <noreply@github.com> | Thu Oct 05 13:25:09 2023 +0000 |
| tree | 4ed0a5a54c4bbba5be1aa0ce92266d6341048589 | |
| parent | 24d80e165b816dfde21d32c31f8554fedba20647 [diff] |
[Torch] Assume strict symbolic shapes (#15107) In nearly all real world models, dynamic numpy style broadcasting never occurs, and managing such cases leads to troublingly pessimistic lowerings and restricts later optimization. This defaults all dynamic symbols coming from pytorch to be interpreted strictly, meaning it must represent an actual size (not something that can optionally be 1).
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.