commit | a3287619af41dc0a0911f2f81ab93929e1bc60f0 | [log] [tgz] |
---|---|---|
author | Geoffrey Martin-Noble <gcmn@google.com> | Wed Aug 25 10:53:26 2021 -0700 |
committer | GitHub <noreply@github.com> | Wed Aug 25 10:53:26 2021 -0700 |
tree | c2967d1c37b2323d57830cf769d11c887d7b523e | |
parent | 7660e49277749c6a9241d8179c362a0b6dbd744b [diff] |
Rename Bazel repo iree_vulkan_headers to vulkan_headers (#6862) TensorFlow used to make it impossible to name Bazel repositories the same as theirs because they didn't use `maybe`. Now `tf_http_archive` performs maybe-like behavior and skips the repo if one with the same name already exists. So now we can use the more normal name for this Bazel repo. This makes the vulkan headers Bazel repo behave like the others in the TF build and use the IREE submodule instead of an `http_archive` from TF. Note though, that the only usage of `@vulkan_headers` in TF is in a part of a build that we don't use (TFLite GPU delegate) and uses a target we don't define ("vulkan_headers_no_prototypes"): https://github.com/tensorflow/tensorflow/blob/1b82ae90a4/tensorflow/lite/delegates/gpu/BUILD#L207
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.