From 1b7f529c5c1d4277a63976e712e7be36e0a0a067 Mon Sep 17 00:00:00 2001 From: tong-shao <59794204+tong-shao@users.noreply.github.com> Date: Tue, 25 May 2021 10:51:11 +0800 Subject: [PATCH] update readme-v0.3 release (#274) * update readme-v0.3 release * Update e2e_evaluator.py Co-authored-by: Wenxiang Hu --- README.md | 4 +++- docs/README.md | 4 +++- test/nnfusion/scripts/evaluator/e2e_evaluator.py | 2 +- 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 0f5980b1b..401d0f211 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ - Developers who want to deploy their pre-trained model as framework-free source codes with minimum library dependencies. - Researchers who want to quickly try new compiler optimization ideas or customize optimizations on some specific models. -### [NNFusion v0.2 has been released!](https://github.com/microsoft/nnfusion/releases/tag/v0.2):raised_hands: +### [NNFusion v0.3 has been released!](https://github.com/microsoft/nnfusion/releases/tag/v0.3):raised_hands: ## Highlight features - Provide a full-stack optimization mechanism, including: @@ -94,6 +94,8 @@ For more detailed information on NNFusion usage, please refer to [NNFusion Usage For TensorFlow users, you can refer to [Kernel Tuner Tutorial](https://github.com/microsoft/nnfusion/blob/master/docs/Compile-a-model-with-kernel-tuning-enabled.md) to learn how to compile a TensorFlow model and tune each operator in this model to generate the end-to-end source code. +For detailed example about trainingļ¼Œplease refer to [How to use NNFusion Python interface for inference/training](https://github.com/microsoft/nnfusion/tree/master/src/python/example). + ### Build from Source Code Researchers or contributors who want to do more research on optimizing model compilation, you can build NNFusion from source code. To build from source code, please read the following documents: diff --git a/docs/README.md b/docs/README.md index 0bca5688a..0248c2677 100644 --- a/docs/README.md +++ b/docs/README.md @@ -7,8 +7,10 @@ Welcome to the NNFusion Documents! - [Adding-Custom-Operator](/src/contrib/custom_op/README.md) 2. [Build-Guide](Build-Guide.md) - [End-to-end-Test](End-to-end-Test.md) -3. [Compile-a-Tensorflow-model-with-NNFusion](Compile-a-Tensorflow-model-with-NNFusion.md) +3. How to compile model with NNFusion + - [Compile-a-Tensorflow-model-with-NNFusion](Compile-a-Tensorflow-model-with-NNFusion.md) - [Compile-a-model-with-kernel-tuning-enabled](Compile-a-model-with-kernel-tuning-enabled.md) + - [How to use NNFusion Python interface for inference/training](../src/python/example/README.md) 4. [Guide-for-Contributors](Guide-for-Contributors.md) - [Contribution-Guide](Contribution-Guide.md) - [Coding-Guide](Coding-Guide.md) diff --git a/test/nnfusion/scripts/evaluator/e2e_evaluator.py b/test/nnfusion/scripts/evaluator/e2e_evaluator.py index d8f45ca7a..df5a1dc27 100644 --- a/test/nnfusion/scripts/evaluator/e2e_evaluator.py +++ b/test/nnfusion/scripts/evaluator/e2e_evaluator.py @@ -15,7 +15,7 @@ def __init__(self, testcase, codegen_folder = "cuda_codegen", default_device = " self.nnfusion_cli = nnfusion_cli self.nnfusion_cli_arg = nnfusion_cli_arg - self.perf_mode = True + self.perf_mode = False self.latency = 0 def load_default_nnfusion_cli(self):