| commit | 479f4ed25a834939daae2bfb67affd9fc5ee98c7 | [log] [tgz] |
|---|---|---|
| author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | Wed Oct 18 20:25:49 2023 -0700 |
| committer | GitHub <noreply@github.com> | Thu Oct 19 03:25:49 2023 +0000 |
| tree | 78e235bd76c872401ce10db48b22364aaaf59026 | |
| parent | add9417113df221d07d717b99e6c9f0637b6d830 [diff] |
[mlir][Flow] Reland https://github.com/openxla/iree/pull/14656 but keep `CollapseReductionDims` pass (#15219) https://github.com/openxla/iree/pull/14656 attempted to keep a single collapse dimensions pass. But there are some cases that slip through that cause a segfault in the GPU backends (https://github.com/openxla/iree/issues/15088) . Supporting those cases turn out to be actually involved. While figuring out, relanding the earlier commit to keep the gains that were made there.
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.