| commit | b78340f4113baad13fc589178dd8f1e95a46fd20 | [log] [tgz] |
|---|---|---|
| author | mariecwhite <mariewhite@google.com> | Sat Feb 11 22:34:19 2023 -0800 |
| committer | GitHub <noreply@github.com> | Sun Feb 12 17:34:19 2023 +1100 |
| tree | a0da36b5057b934fec97341d5314c8e3cf9e46e1 | |
| parent | d77cb68d69f52c78583c9e57c9f00ee269ced59f [diff] |
Add Bert-Large to x86 and CUDA benchmarks (#12032) Adds Bert-Large with input sequence length 384, 345M param model. This version is taken from the MLPerf repo: https://github.com/mlcommons/inference/tree/master/language/bert. Some modifications to the code was made to save it in Saved Model format. Steps to reproduce: https://gist.github.com/mariecwhite/e61ccebd979d98d097946ac7725bcc29
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.