Google Git
Sign in
opensecura / 3p / openxla / iree / 60843ecad5fe49301e036a7c2690378f974ab07f
commit60843ecad5fe49301e036a7c2690378f974ab07f[log] [tgz]
authorKunwar Grover <groverkss@gmail.com>Wed Sep 11 16:33:44 2024 +0100
committerGitHub <noreply@github.com>Wed Sep 11 16:33:44 2024 +0100
treeea2adb1918405d580017379e2294c874d7ead06f
parentc3cbfbd0cb5e345380deaf8b88938030d30961f9 [diff]
[VectorDistribution] Add support for multi-subgroup attention (#18188)

This patch adds support for distributing attention to multiple
subgroups.

Currently, we distinguish the two matmuls in attention by setting a
discardable attribute on the matmuls (set during decomposition) used as
a hint to layout anchoring, on what to do when it encounters these
matmuls. (Note that even if these hints were dropped, it would only lead
to a drop in performance, because the layout anchoring doesn't know its
attention anymore). The correct way to handle these matmuls would be to
start putting mma_schedule as an operation specific lowering config and
teach decomposition to propagate this lowering to the two matmuls after
decomposition. This is blocked by work on TileAndDistributeToWorkgroups
supporting consumer fusion, and needs some heavy lifting.
6 files changed
tree: ea2adb1918405d580017379e2294c874d7ead06f
  1. .github/
  2. build_tools/
  3. compiler/
  4. docs/
  5. experimental/
  6. integrations/
  7. lib/
  8. llvm-external-projects/
  9. runtime/
  10. samples/
  11. tests/
  12. third_party/
  13. tools/
  14. .bazel_to_cmake.cfg.py
  15. .bazelignore
  16. .bazelrc
  17. .bazelversion
  18. .clang-format
  19. .dockerignore
  20. .git-blame-ignore-revs
  21. .gitattributes
  22. .gitignore
  23. .gitmodules
  24. .pre-commit-config.yaml
  25. .yamllint.yml
  26. AUTHORS
  27. BUILD.bazel
  28. CITATION.cff
  29. CMakeLists.txt
  30. configure_bazel.py
  31. CONTRIBUTING.md
  32. LICENSE
  33. MAINTAINERS.md
  34. README.md
  35. RELEASING.md
  36. 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.

IREE Discord Status pre-commit OpenSSF Best Practices

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

Release status

PackageRelease status
GitHub release (stable)GitHub Release
GitHub release (nightly)GitHub Release
Python iree-compilerPyPI version
Python iree-runtimePyPI version

Build status

CI PkgCI

Host platformBuild status
LinuxCI - Linux x64 clang
CI - Linux arm64 clang
macOSCI - macOS x64 clang
WindowsCI - Windows x64 MSVC

For the full list of workflows see https://iree.dev/developers/general/github-actions/.

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

Community meeting recordings: IREE YouTube channel

  • 2021-06-09: IREE Runtime Design Tech Talk (recording and slides)
  • 2020-08-20: IREE CodeGen: MLIR Open Design Meeting Presentation (recording and slides)
  • 2020-03-18: Interactive HAL IR Walkthrough (recording)
  • 2020-01-31: End-to-end MLIR Workflow in IREE: MLIR Open Design Meeting Presentation (recording and slides)

License

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