commit | 108e050bb707dfae4e7e4d8b52759bd795b52a97 | [log] [tgz] |
---|---|---|
author | Rob Suderman <suderman@google.com> | Mon Jul 22 15:34:35 2024 -0700 |
committer | GitHub <noreply@github.com> | Mon Jul 22 15:34:35 2024 -0700 |
tree | 27553bf0c132bae9b331c76f99521b22a23d6620 | |
parent | 1dcc62e1d563cdb7085ef6223b591730379c0904 [diff] |
Make fp8 attention using static quantized softmax (#17949) Added a flag that uses a statically selected softmax range for fp8 attention. This allows the value to be tuned without plumbing through the attention operation. Eventually this should be a parameter passed to `linalg_ext.attention`.
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.