commit | 88d5e1b96e06973becb8f942d849a4eb1cb725e4 | [log] [tgz] |
---|---|---|
author | not-jenni <59985653+not-jenni@users.noreply.github.com> | Wed May 12 09:16:48 2021 -0700 |
committer | GitHub <noreply@github.com> | Wed May 12 09:16:48 2021 -0700 |
tree | 733cfb2181dd117ec96f327e496e0ed9c15ea581 | |
parent | 783e5e369c6db7a48bd9c8cfa4240dce3c39fa51 [diff] | |
parent | 953a98c21e654e1a74cf4701fd1a01612ddd6a4d [diff] |
Merge google -> main (#5856) * 953a98c21 Integrate LLVM at llvm/llvm-project@b7a11274f90f * e7f75827f Integrate LLVM at llvm/llvm-project@34c098b780a2 * 92ddee60c [TF:XLA:MLIR] Add support for tf.Mean on ranked dynamic shapes * 619265c93 Integrate LLVM at llvm/llvm-project@6351993da72e * 4dfa270e2 Integrate LLVM at llvm/llvm-project@23596fece043 * 82a0ec18a Integrate LLVM at llvm/llvm-project@3f8be15f2911 * 3a6332b5c Merge main -> google * 0c79bfaa4 Integrate LLVM at llvm/llvm-project@fec294599894 * b7f613344 Synchronize submodules with LLVM at llvm/llvm-project@df47368d406a * 9df58ec08 Integrate LLVM at llvm/llvm-project@df47368d406a * 1f1e15cc9 Integrate LLVM at llvm/llvm-project@88a48999d249 * 9ad4c4bc0 Integrate LLVM at llvm/llvm-project@888307ee625b * d5d6d3787 Integrate LLVM at llvm/llvm-project@1e11616a071d * af614e13e Integrate LLVM at llvm/llvm-project@bf812ea484b7
IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler that lowers Machine Learning (ML) models to a unified IR optimized for real-time inference on mobile/edge devices against heterogeneous hardware accelerators. IREE also provides flexible deployment solutions for its compiled ML models.
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!
IREE is licensed under the terms of the Apache license. See LICENSE for more information.