| commit | 0acd6ec7af2299f76c551d85c4123fa40be2658c | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scotttodd@google.com> | Mon May 23 15:53:30 2022 -0700 |
| committer | GitHub <noreply@github.com> | Mon May 23 15:53:30 2022 -0700 |
| tree | 7941babf58d496c1eb8fe0db41f69859af8209a5 | |
| parent | ef81a945b0db4b771183e4a9042f5cda28258f14 [diff] |
Add dark mode architecture diagram to README and website. (#9192) GitHub and mkdocs-material both now support including light and dark mode versions of images. We can use this to show a more natural project architecture diagram based on the current website theme, fixing https://github.com/google/iree/issues/7140. --- Live Previews (until this PR gets merged): | | Before (always light mode) | After (with light and dark) | | - | - | - | | website | https://google.github.io/iree/#project-architecture | https://scotttodd.github.io/iree/#project-architecture | | readme | https://github.com/google/iree#architecture-overview | https://github.com/ScottTodd/iree/tree/diagram-dark-mode#architecture-overview | Screenshots: light on light:  light on dark:  (this PR replaces this with dark on dark) dark on dark:  (new with this PR) --- References: * https://www.stefanjudis.com/notes/how-to-define-dark-light-mode-images-in-github-markdown/ * https://github.blog/changelog/2021-11-24-specify-theme-context-for-images-in-markdown/ * https://github.blog/changelog/2022-05-19-specify-theme-context-for-images-in-markdown-beta/ Note: the `<picture>` syntax suggested in the recent GitHub blog post just directly passes through the element contents, so relative paths to files in the repository do not work (yet?). Because of that, I've opted to use the non-standard `#gh-dark-mode-only`/`#gh-light-mode-only` selectors. These are implemented in GitHub, mkdocs-material, and in VSCode's markdown preview, but other markdown renderers may display both the light and dark mode images, instead of one or the other.
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!
| CI System | Build System | Platform | Architecture | Configuration / Component | Status |
|---|---|---|---|---|---|
| Kokoro | Bazel | Linux | x86-64 |  | |
| Kokoro | CMake & Bazel | Linux | x86-64 (swiftshader) | Integrations |  |
| Kokoro | CMake & Bazel | Linux | x86-64 (turing) | Integrations |  |
| Kokoro | CMake | Linux | x86-64 (swiftshader) |  | |
| Kokoro | CMake | Linux | x86-64 (swiftshader) | asan |  |
| Kokoro | CMake | Linux | x86-64 (turing) |  | |
| Kokoro | CMake | Android | arm64-v8a | Runtime (build only) |  |
| Kokoro | CMake | Bare Metal | risc-v-32 | Runtime |  |
| Kokoro | CMake | Linux | risc-v-64 | Runtime |  |
| Buildkite | CMake | Android | arm64-v8a | Runtime |  |
| BuildKite | CMake | Android | arm64-v8a | Runtime Benchmarks |  |
| BuildKite | CMake | Linux | x86-64 | Tracing + Standalone Runtime |  |
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.
