Google Git
Sign in
opensecura / 3p / openxla / iree / c121b868ee12fd7ac3d60ea2912c248a328b09a8
commitc121b868ee12fd7ac3d60ea2912c248a328b09a8[log] [tgz]
authorScott Todd <scott.todd0@gmail.com>Mon Feb 12 16:32:05 2024 -0800
committerGitHub <noreply@github.com>Mon Feb 12 16:32:05 2024 -0800
tree75748c281ea899e801d1bd719d540f9bb519248d
parent246edee03074f6f8126aa3f6ae7d815f32f245d9 [diff]
Add documentation guide for parameters. (#16382)

This adds a new guide to the website explaining what "parameters" are in
IREE and walking through a few ways to work with them.

A few sections are not yet completed, but this should be enough to
introduce some of the concepts and get people started.

**Notable omissions** that I'm aware of (these can/should be documented
but I haven't written the content yet):
* Existing `.mlir` with embedded weights --> `.irpa` file by using
`--iree-io-export-parameters`
* Existing `.mlir` with parameters + `.irpa` file --> `.mlir` with
embedded weights by using `--iree-io-import-parameters` (this pass does
not exist yet)
* More concrete examples (e.g. Colab notebooks) of working with GGUF /
Safetensors
* Scopes and overlays
* Sharding of `.irpa` files
* Concrete examples of using splats for developer workflows
* Reading _and_ writing parameters (training loops)
* Custom parameter indices (e.g. Python/Java/etc. code loading from
memory or the network, or cuFile/DirectStorage)

Progress on https://github.com/openxla/iree/issues/14987
3 files changed
tree: 75748c281ea899e801d1bd719d540f9bb519248d
  1. .devcontainer/
  2. .github/
  3. build_tools/
  4. compiler/
  5. docs/
  6. experimental/
  7. integrations/
  8. lib/
  9. llvm-external-projects/
  10. runtime/
  11. samples/
  12. tests/
  13. third_party/
  14. tools/
  15. .bazel_to_cmake.cfg.py
  16. .bazelignore
  17. .bazelrc
  18. .bazelversion
  19. .clang-format
  20. .dockerignore
  21. .git-blame-ignore-revs
  22. .gitignore
  23. .gitmodules
  24. .yamllint.yml
  25. AUTHORS
  26. BUILD.bazel
  27. CITATION.cff
  28. CMakeLists.txt
  29. configure_bazel.py
  30. CONTRIBUTING.md
  31. LICENSE
  32. README.md
  33. WORKSPACE
README.md

IREE: Intermediate Representation Execution Environment

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.

CI Status IREE Discord Status

Project Status

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!

Communication Channels

Related Project Channels

  • MLIR topic within LLVM Discourse: IREE is enabled by and heavily relies on MLIR. IREE sometimes is referred to in certain MLIR discussions. Useful if you are also interested in MLIR evolution.

Architecture Overview

IREE Architecture IREE Architecture

See our website for more information.

Presentations and Talks

License

IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.