commit | 514b7aa6748488b5e2dc7b76afb9f60bc1bff8e0 | [log] [tgz] |
---|---|---|
author | Ben Vanik <benvanik@google.com> | Fri Aug 13 14:07:12 2021 -0700 |
committer | GitHub <noreply@github.com> | Fri Aug 13 14:07:12 2021 -0700 |
tree | 03d83375d0bacaacab28118a39c48b4a30e311d0 | |
parent | 46b7164f52791476e75ab8db86023324d4ceaa2b [diff] | |
parent | 006da8df2c8e2fe20cd97db83c5639d1bf6de177 [diff] |
Removing HAL ops that are unused and difficult to support long-term. (#6763) * Removing hal.buffer_view.subview. It will not work for anything but dense tensors and it should be needed. The aliasing also complicates things. * Removing hal.buffer_view.compute_offset/compute_range. Buffer views are fully type erased and these won't work when we have non-dense tensors.
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!
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.