commit | 9c85e30df30d6efcf68a7a1b594e89322bd6085d | [log] [tgz] |
---|---|---|
author | Stella Laurenzo <stellaraccident@gmail.com> | Sat Nov 02 09:18:23 2024 -0700 |
committer | GitHub <noreply@github.com> | Sat Nov 02 09:18:23 2024 -0700 |
tree | ff3672ccd82cd927716dce1e26bcb91dfcb12473 | |
parent | c3b1e6e9ea38a60b3283bf707d6caea3613431f8 [diff] |
[iree.build] Implement iree-compile action. (#18993) This covers a lot of ground to actually get the full compile pipeline working: * Adds dep metadata and uses it to plumb input type to the compiler. * Fully generalizes arg parsing and management. * Adds a skeleton TargetMachine (used to drive the compiler) and teaches it how to handle/pass-through standard IREE flags for simple single device configurations. (Complex cases will be handled with some kind of machine spec file and additional compiler entry-points for setting raw target info). * Plumbs through both in process and out of process compiler invocation. * Robustifies the iree.compiler.api so that it can't do out of order destruction during process cleanup. Much more to do: * I've got enough now to add a torch.export action to iree-turbine. That will be run against the out of process pool. * Quite a bit of compiler invocation ergonomics needed (reproducers, error/output handling, etc). * Need to take a pass through and make pretty console reporting/logging throughout. --------- Signed-off-by: Stella Laurenzo <stellaraccident@gmail.com>
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
Package | Release status |
---|---|
GitHub release (stable) | |
GitHub release (nightly) | |
Python iree-compiler | |
Python iree-runtime |
Host platform | Build status |
---|---|
Linux | |
macOS | |
Windows |
For the full list of workflows see https://iree.dev/developers/general/github-actions/.
See our website for more information.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.