diff options
| author | Rickard Bolin <rickard.bolin@arm.com> | 2024-05-20 13:22:20 +0000 |
|---|---|---|
| committer | Rickard Bolin <rickard.bolin@arm.com> | 2024-05-21 12:55:36 +0000 |
| commit | 7abd82a6cd58d36a512897984b42522db500e308 (patch) | |
| tree | 0e1cfa9cf5fb8a3a087d05c55e260af7082f3580 | |
| parent | 3955765d971d75571484c8b4ae3c6abc034678ea (diff) | |
| download | ethos-u-vela-7abd82a6cd58d36a512897984b42522db500e308.tar.gz | |
MLBEDSW-9089: Update release notes3.12.0.rc23.12.0
- Add release notes for 3.12.0
- Update README with supported TensorFlow version
Change-Id: Ia95955e9fbe824d1dc62e3960a9ed43fa3689de5
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
| -rw-r--r-- | README.md | 5 | ||||
| -rw-r--r-- | RELEASES.md | 18 |
2 files changed, 21 insertions, 2 deletions
@@ -1,5 +1,5 @@ <!-- -SPDX-FileCopyrightText: Copyright 2020-2023 Arm Limited and/or its affiliates <open-source-office@arm.com> +SPDX-FileCopyrightText: Copyright 2020-2024 Arm Limited and/or its affiliates <open-source-office@arm.com> SPDX-License-Identifier: Apache-2.0 @@ -50,7 +50,8 @@ optimised operators against that of the corresponding TensorFlow Lite reference kernels (or TensorFlow Lite for Microcontrollers reference kernels in the case of the UNIDIRECTIONAL_SEQUENCE_LSTM operator). The following list indicates which version is used for comparison: -* Vela 3.11.0 to current supports TensorFlow 2.15 +* Vela 3.12.0 to current supports TensorFlow 2.16 +* Vela 3.11.0 supports TensorFlow 2.15 * Vela 3.10.0 supports TensorFlow 2.14 * Vela 3.9.0 supports TensorFlow 2.12 * Vela 3.8.0 supports TensorFlow 2.11 diff --git a/RELEASES.md b/RELEASES.md index 27d52837..a3b41b5b 100644 --- a/RELEASES.md +++ b/RELEASES.md @@ -22,6 +22,24 @@ main feature changes, interface changes and reported defects that have been fixed. The version numbering adheres to the [semantic versioning](https://semver.org/) scheme. +## Release 3.12.0 - 20/05/2024 + +**Main feature changes:** + +* Extended operator support: STRIDED_SLICE with strides in H/W > 1 +* Upgrade TensorFlow Lite support to version 2.16 + +**Interface changes:** + +* None + +**Reported defect fixes:** + +* Fixed CONCAT operators split between multiple subgraphs (MLCE-1223 & MLCE-1252) +* Fixed issue with combining STRIDED_SLICE operation with elementwise broadcasting (MLCE-1223) +* Fixed issue with LUT index calculation and STRIDED_SLICE optimisation (MLCE-1253) + + ## Release 3.11.0 - 19/02/2024 **Main feature changes:** |