| commit | 256fe4fd70fd82d6b1bf85a7327cdee1f5954df8 | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scotttodd@google.com> | Tue Oct 31 16:38:32 2023 -0700 |
| committer | GitHub <noreply@github.com> | Tue Oct 31 16:38:32 2023 -0700 |
| tree | 74c9691baa5780539d5c78c3bdadcc7b679cfb5f | |
| parent | 522359618a05a40aef78c8cc020884f1908226f4 [diff] |
Add "torch" as an `InputType` in `iree/compiler/tools/core.py`. (#15358) Progress on https://github.com/openxla/iree/issues/15353 * This fixes `binary = iree.compiler.tools.compile_file("path.mlir", input_type="torch", ...)` * Still need "auto" handling of the "torch" input type We should also add some tests in-tree that use the torch dialect(s). I can help there, but I need to think through a few details first (how to generate / update test files, where to put the tests, etc.)
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.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.