commit | 5f1bbebe3a7962ee5b3bc3748772a296c4b4ad33 | [log] [tgz] |
---|---|---|
author | Geoffrey Martin-Noble <gcmn@google.com> | Wed Jul 13 10:53:26 2022 -0700 |
committer | GitHub <noreply@github.com> | Wed Jul 13 10:53:26 2022 -0700 |
tree | 86591bdca383ad82c47c501b4ff2e2c7398b630f | |
parent | 245c70ef28ec5bdfa74b73c52a221e700d1b52f6 [diff] |
Add a workflow for building and testing the runtime post-submit (#9774) This uses GitHub's hosted runners, since they are sufficient when only building the runtime. It mostly a step towards migrating our initial Buildkite workflows and finding parity with those. Note that this is not doing anything to make the entire workflow idempotent. We will likely need to move to our own artifact storage scheme (backed by GCS) to make that work. We definitely incur a cost from having to upload and download the build directory rather than building and testing in the same directory (1.5 minutes to upload. download is negligible), but I think the modularity is worth it and we can find a way to speed it up.
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.