commit | 6a82eb5065742fa4498b0bc85eb5f01271b20a65 | [log] [tgz] |
---|---|---|
author | Stanley Winata <68087699+raikonenfnu@users.noreply.github.com> | Tue Jul 16 10:13:51 2024 -0700 |
committer | GitHub <noreply@github.com> | Tue Jul 16 10:13:51 2024 -0700 |
tree | 94c261ab4624ba60a2a29efa0dd6a7e9309ca98d | |
parent | c12d066fdb5611c752569a15e14b41f51c5397f6 [diff] |
Add F8_16x16x32_F32 support for MFMA (#17792) Added F8_16x16x32xF32 MFMA layout support and their e2e tests. Needed to adjust/branch in the e2e matmul test's cmake because only gfx94x GPUs have FP8 MFMA layouts and it has different I8 intrinsic shape/layout as opposed to what is present in gfx90x.
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.