commit | 9d2d7668420ebb7f060b8c0a8f3b770fd97ab97c | [log] [tgz] |
---|---|---|
author | Stanley Winata <68087699+raikonenfnu@users.noreply.github.com> | Thu Jul 11 12:44:21 2024 -0700 |
committer | GitHub <noreply@github.com> | Thu Jul 11 12:44:21 2024 -0700 |
tree | 3d5454b3127836a3fd4c60a7c9cdf0da46784bbd | |
parent | 20d830887dd478dfb467d5f657afc9daea3d7baf [diff] |
[LinalgExt] Adding IndexingMaps to linalg_ext.attentionOp (#17864) In order to make fusion with other generics, specifically transpose easier, we introduce affineMaps/indexingMaps to linalg_ext.attentionOp. With that we are also enforcing the number and types of dpsInputs. We are also removing "transpose_V" attribute in lieu of infering from indexingMaps. --------- Co-authored-by: Kunwar Grover <groverkss@gmail.com>
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.
Community meeting recordings: IREE YouTube channel
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.