From cbb08925b08ca3e1197f0265e6638060c51c7a67 Mon Sep 17 00:00:00 2001 From: Konrad Nowicki Date: Thu, 5 Dec 2024 19:36:44 +0100 Subject: [PATCH] Changelog update - tested on tools --- CHANGELOG.md | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 61ea55cf..358e22d7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -16,7 +16,8 @@ limitations under the License. # Changelog -## 0.13.0 (unreleased) +## 0.13.0 + - new: Introducing custom_args in TensorConfig for custom runners to use which allows dynamic shapes setup for TorchTensorRT compilation - new: autocast_dtype added Torch runner configuration to set the dtype for autocast @@ -33,6 +34,21 @@ limitations under the License. - fix: Warn when using autocast with bfloat16 in Torch - fix: Pass runner configuration to runners in nav.profile +[//]: <> (put here on external component update with short summary what change or link to changelog) + +- Version of external components used during testing: + - [PyTorch 2.6.0a0+df5bbc0](https://github.com/pytorch/pytorch/commit/df5bbc09d191fff3bdb592c184176e84669a7157) + - [TensorFlow 2.16.1](https://github.com/tensorflow/tensorflow/releases/tag/v2.16.1) + - [TensorRT 10.6.0.26](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html) + - [Torch-TensorRT 2.6.0a0](https://github.com/NVIDIA/Torch-TensorRT) + - [ONNX Runtime 1.19.2](https://github.com/microsoft/onnxruntime/releases/tag/v1.19.2) + - [Polygraphy](https://github.com/NVIDIA/TensorRT/tree/master/tools/Polygraphy/): 0.49.13 + - [GraphSurgeon](https://github.com/NVIDIA/TensorRT/tree/master/tools/onnx-graphsurgeon/): 0.5.2 + - [tf2onnx v1.16.1](https://github.com/onnx/tensorflow-onnx/releases/tag/v1.16.1) + - Other component versions depend on the used framework containers versions. + See its [support matrix](https://docs.nvidia.com/deeplearning/frameworks/support-matrix/index.html) + for a detailed summary. + ## 0.12.0 - new: simple and detailed reporting of the optimization process