commit | 698b75c4cd0d0f1c3103d9b780bfc8385aaa6598 | [log] [tgz] |
---|---|---|
author | Ian Wood <75152913+IanWood1@users.noreply.github.com> | Wed Jul 03 11:22:26 2024 -0700 |
committer | GitHub <noreply@github.com> | Wed Jul 03 11:22:26 2024 -0700 |
tree | c97058f88bd71f066e51f20896e8c8171b163bb5 | |
parent | 6f268810eb1edb6ee3df60e1f7b037014fe37c10 [diff] |
[Flow][Global Opt] Fold global unit dims (#17781) Currently reverting [7884dc8](https://github.com/iree-org/iree/commit/7884dc8a2009d86b809161dffbb6ac8c2b68bdf0) to test regressions (there were problems with llama). Issue here https://github.com/nod-ai/SHARK-Turbine/issues/756 Couldn't reproduce the issue with llama yet. It might be best to land this since the unit dims should be folded in general, it just doesn't play well with this model in particular. Signed-off-by: Ian Wood <ianwood2024@u.northwestern.edu>
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.