| commit | 123b7e65de1aababae43d8b8364f00e48ac6a714 | [log] [tgz] |
|---|---|---|
| author | Ben Vanik <ben.vanik@gmail.com> | Tue Mar 21 07:51:04 2023 -0700 |
| committer | GitHub <noreply@github.com> | Tue Mar 21 10:51:04 2023 -0400 |
| tree | ee6032fd4dba1e5629224cfa4c68f65f5c6f75eb | |
| parent | 2c51f7bb0a31cc8c0ad1cdca9c0d29070a3d825a [diff] |
Adding better diagnostics on input shape mismatch. (#12622) The messages are now clearer when scalar tensors are used and we infer arg/result names to pass down instead of just using 'tensor'. This produces messages like: ``` buffer_diagnostics.c:225: INVALID_ARGUMENT; input 1 shape dimension 0 mismatch; expected 4 but have 409; expected shape `4`, actual shape `409`; while invoking native function hal.buffer_view.assert; while calling import; ``` I haven't done a survey to see if there's anything closer to frontends we can use to get better names but we at least have something now and a placeholder of where such name inference could live.
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.