commit | d3770ff64885d65a558b4f91ee12d10a9deeea47 | [log] [tgz] |
---|---|---|
author | Stella Laurenzo <stellaraccident@gmail.com> | Mon Oct 18 22:54:18 2021 -0700 |
committer | GitHub <noreply@github.com> | Mon Oct 18 22:54:18 2021 -0700 |
tree | 0158c5bd52864244edacf7a03987acad559491d4 | |
parent | e5408e9f40c3f0059d01867af31208379386dc1d [diff] |
Add IREE_BUILD_TRACY CMake option. (#7382) * Off by default for now, and I only expect that this works on Linux. * If `-DIREE_BUILD_TRACY=ON` then `ninja tracy/all` will build both the headless capture tool and the full GUI (if sufficient deps are installed). * My intent is, in a next step, to enable a traced runtime Python wheel as an alternative to the normal IREE runtime, and in that, I will include the headless capture tool. * Add scripts to install deps on manylinux2014 to build Tracy. * Add console scripts to iree.runtime Python package to bundle iree-tracy-capture and iree-run-module (because why not while here). * Add an instrumented runtime package variant to the release pipeline.
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.