commit | bddde2cb9fce8c4782906908a0f39451df2e54f0 | [log] [tgz] |
---|---|---|
author | Geoffrey Martin-Noble <gcmn@google.com> | Mon Jul 18 10:59:28 2022 -0700 |
committer | GitHub <noreply@github.com> | Mon Jul 18 10:59:28 2022 -0700 |
tree | 5f915ec7bbbc357921da8c2bb0b94e6ad2607f2a | |
parent | 25e81fe4089da65ab38c54e158aa242add944a9c [diff] |
Check in scripts to deploy on GitHub runners (#9765) There's one script that we can bake into the disk image in the runner home directory. It fetches the other configuration into a subdirectory. The `actions-runner/.env` is symlinked to `config/runner.env` in the runner disk image. This uses a proxy to fetch registration tokens without giving the runners themselves access to powerful administration privileges. See https://github.com/google-github-actions/github-runner-token-proxy GitHub actions on pull requests currently require approval for non-collaborators and the runners do not yet have any special privileges, so it shouldn't be a problem that they're not yet ephemeral (which requires setting up some additional teardown logic).
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.