v0

Author: nan

docs/backend-reference/torch.mdx

@@ -148,7 +148,7 @@ For quantizing onnx models using tensorrt, the following parameters are availabl
 
 
 
-See [example](https://github.com/torchpipe/torchpipe/tree/main/examples/int8). 
+See [example](https://github.com/torchpipe/torchpipe/tree/v0/examples/int8). 
 
 
 ### Forward Computation

docs/benchmark.mdx

@@ -67,7 +67,7 @@ Client 10/Compute Backend Instance 1/Timeout 0/Max Batch 1
 |    triton-cli     | QPS: 15039 <br />   | -                  |
 
 
-[import]: https://github.com/torchpipe/torchpipe/blob/main/libs/commands/import/README.md
+[import]: https://github.com/torchpipe/torchpipe/blob/v0/libs/commands/import/README.md
 
 
 

docs/contribution_guide/modify_the_code.md

@@ -28,5 +28,5 @@ pytest .
 If necessary, please consider supplementing with [Python tests](https://github.com/torchpipe/torchpipe//test).
 
 :::note Code Formatting (optional)
-Please configure a formatting plugin to enable [.clang-format](https://github.com/torchpipe/torchpipe/blob/develop/.clang-format).
+Please configure a formatting plugin to enable [.clang-format](https://github.com/torchpipe/torchpipe/blob/v0/.clang-format).
 :::

docs/installation.mdx

@@ -36,8 +36,7 @@ If you encounter any compilation or runtime issues inside the Docker container,
 First, clone the code:
 
 ```bash
-git clone https://github.com/torchpipe/torchpipe.git
-# git clone -b main https://github.com/torchpipe/torchpipe.git
+git clone  -b v0 https://github.com/torchpipe/torchpipe.git
 cd torchpipe/ && git submodule update --init --recursive
 ```
 
@@ -146,7 +145,7 @@ For more examples, see [Showcase](./showcase/showcase.mdx).
 
 ## Customizing Dockerfile {#selfdocker}
 
-Refer to the [example Dockerfile](https://github.com/torchpipe/torchpipe/blob/main/docker/Dockerfile). 
+Refer to the [example Dockerfile](https://github.com/torchpipe/torchpipe/blob/v0/docker/Dockerfile). 
 
 ```bash
 

docs/python/test.mdx

@@ -392,7 +392,7 @@ def test_all_files(file_dir:str, num_clients=10, batch_size = 1,
 
 
 ### Clients with Different Batch Sizes
-In the example provided [here](https://github.com/torchpipe/torchpipe/blob/main/examples/yolox/yolox_multithreads_test.py), we use ten clients, each requesting different amounts of data per request, ranging from 1 to 10. We validate the consistency of the results in this case.
+In the example provided [here](https://github.com/torchpipe/torchpipe/blob/v0/examples/yolox/yolox_multithreads_test.py), we use ten clients, each requesting different amounts of data per request, ranging from 1 to 10. We validate the consistency of the results in this case.
 
 Typically, users can iterate through all the data in a directory and repeatedly send requests to verify the stability and consistency of the results.
 

docs/quick_start_new_user.md

@@ -7,7 +7,7 @@ type: explainer
 
 # Trial in 30mins(new users)
 
-TorchPipe is a multi-instance pipeline parallel library that provides a seamless integration between lower-level acceleration libraries (such as TensorRT and OpenCV) and RPC frameworks. It guarantees high service throughput while meeting latency requirements. This document is mainly for new users, that is, users who are in the introductory stage of acceleration-related theoretical knowledge, know some python grammar, and can read simple codes. This content mainly includes the use of torchpipe for accelerating service deployment, complemented by performance and effect comparisons. The complete code of this document can be found at [resnet50_thrift](https://github.com/torchpipe/torchpipe/blob/develop/examples/resnet50_thrift/)。
+TorchPipe is a multi-instance pipeline parallel library that provides a seamless integration between lower-level acceleration libraries (such as TensorRT and OpenCV) and RPC frameworks. It guarantees high service throughput while meeting latency requirements. This document is mainly for new users, that is, users who are in the introductory stage of acceleration-related theoretical knowledge, know some python grammar, and can read simple codes. This content mainly includes the use of torchpipe for accelerating service deployment, complemented by performance and effect comparisons. The complete code of this document can be found at [resnet50_thrift](https://github.com/torchpipe/torchpipe/blob/v0/examples/resnet50_thrift/)。
 
 ## Catalogue
 * [1. Basic knowledge](#1)
@@ -84,7 +84,7 @@ self.classification_engine = torch2trt(resnet50, [input_shape],
 
 ```
 
-The overall online service deployment can be found at [main_trt.py](https://github.com/torchpipe/torchpipe/blob/develop/examples/resnet50_thrift/main_trt.py)
+The overall online service deployment can be found at [main_trt.py](https://github.com/torchpipe/torchpipe/blob/v0/examples/resnet50_thrift/main_trt.py)
 
 :::tip
 Since TensorRT is not thread-safe, when using this method for model acceleration, it is necessary to handle locking (with self.lock:) during the service deployment process.
@@ -104,7 +104,7 @@ From the above process, it's clear that when accelerating a single model, the fo
 
 ![](images/quick_start_new_user/torchpipe_en.png)
 
-We've made adjustments to the deployment of our service using TorchPipe.The overall online service deployment can be found at [main_torchpipe.py](https://github.com/torchpipe/torchpipe/blob/develop/examples/resnet50_thrift/main_torchpipe.py).
+We've made adjustments to the deployment of our service using TorchPipe.The overall online service deployment can be found at [main_torchpipe.py](https://github.com/torchpipe/torchpipe/blob/v0/examples/resnet50_thrift/main_torchpipe.py).
 The core function modifications as follows:
 
 ```py
@@ -219,7 +219,7 @@ std="58.395, 57.120, 57.375" # 255*"0.229, 0.224, 0.225"
 `python clien_qps.py --img_dir /your/testimg/path/ --port 8888 --request_client 20 --request_batch 1
 `
 
-The specific test code can be found at [client_qps.py](https://github.com/torchpipe/torchpipe/blob/develop/examples/resnet50_thrift/client_qps.py)
+The specific test code can be found at [client_qps.py](https://github.com/torchpipe/torchpipe/blob/v0/examples/resnet50_thrift/client_qps.py)
 
 With the same Thrift service interface, testing on a machine with NVIDIA-3080 GPU, 36-core CPU, and concurrency of 10, we have the following results:
 

docs/showcase/showcase.mdx

@@ -17,10 +17,10 @@ slug: /showcase
 | [tensorrt's native int8] |                                        | [TensorrtTensor](../backend-reference/torch.mdx#tensorrttensor)                                           |      |
 
 
-[resnet18]: https://github.com/torchpipe/torchpipe/tree/main/examples/resnet18
-[yolox]: https://github.com/torchpipe/torchpipe/tree/main/examples/yolox
-[PP-OCRv2]: https://github.com/torchpipe/torchpipe/tree/main/examples/ppocr
-[TensorRT's native INT8]: https://github.com/torchpipe/torchpipe/tree/main/examples/int8
+[resnet18]: https://github.com/torchpipe/torchpipe/tree/v0/examples/resnet18
+[yolox]: https://github.com/torchpipe/torchpipe/tree/v0/examples/yolox
+[PP-OCRv2]: https://github.com/torchpipe/torchpipe/tree/v0/examples/ppocr
+[TensorRT's native INT8]: https://github.com/torchpipe/torchpipe/tree/v0/examples/int8
 
 [torchpipe.utils.cpp_extension.load]: ../python/compile.mdx
 [filter]: ../Inter-node/filter.mdx

docs/tools/quantization.mdx

@@ -29,7 +29,7 @@ For detection models, you can consider using the [official complete tutorial](ht
 
 In addition to the pre-training parameters provided by the model for normal training, training-based quantization also requires quantization pre-training parameters provided by post-training quantization (ptq).
 
-We have integrated [calib_tools](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/calib_tools.py) for reference.
+We have integrated [calib_tools](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/calib_tools.py) for reference.
 
 - Define calibrator:
 ```python
@@ -100,17 +100,17 @@ The official training format is very simple and is only used as an example.
 #### Direct Quantization without Modifying Backbone
 Following the official example, we conducted step-by-step experiments on resnet:
 
-- Download training data: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/download_data.py)
-- Train for 10 epochs to obtain the resnet50 model: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/fp32_train.py), accuracy 98.44%
-- (optional) PyTorch ptq: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/ptq.py), accuracy 96.64% (max)
-- (optional) PyTorch qat: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/qat.py), accuracy 98.26%.
+- Download training data: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/download_data.py)
+- Train for 10 epochs to obtain the resnet50 model: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/fp32_train.py), accuracy 98.44%
+- (optional) PyTorch ptq: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/ptq.py), accuracy 96.64% (max)
+- (optional) PyTorch qat: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/qat.py), accuracy 98.26%.
 
 #### MSE + Residual Fusion {#mseadd}
 
 The above resnet training uses the max quantization method and does not fuse the Add layer, resulting in TensorRT running speed not meeting expectations. The following are the results after fusing Add under int8 and switching to the mse mode:
 
-- ptq: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/ptq_merge_residual.py), accuracy 94.34% (mse)
-- qat: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/qat_merge_residual.py), accuracy 95.82%.
+- ptq: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/ptq_merge_residual.py), accuracy 94.34% (mse)
+- qat: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/qat_merge_residual.py), accuracy 95.82%.
 
 
 #### Summary of Results in PyTorch
@@ -124,9 +124,9 @@ The above resnet training uses the max quantization method and does not fuse the
 ### Summary of Test Results in TorchPipe
 The following tests were performed using the onnx generated by TorchPipe:
 
-- Export onnx: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/export_onnx_merge_residual.py)
-- Load fp32-onnx with TorchPipe and perform ptq: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/torchpipe_ptq_test.py)
-- Test with qat-onnx loaded with TorchPipe: [code](https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/torchpipe_qat_test.py)
+- Export onnx: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/export_onnx_merge_residual.py)
+- Load fp32-onnx with TorchPipe and perform ptq: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/torchpipe_ptq_test.py)
+- Test with qat-onnx loaded with TorchPipe: [code](https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/torchpipe_qat_test.py)
 
 
 | Model                  | Accuracy | Performance | Note                                |
@@ -135,4 +135,4 @@ The following tests were performed using the onnx generated by TorchPipe:
 | tensorrt's native int8 | 98.26%   | -           |                                     |
 | qat                    | 98.67%   | -           | [Acc. under onnxruntime] is 98.69%. |
 
-[Acc. under onnxruntime]: https://github.com/torchpipe/torchpipe/blob/develop/examples/int8/qat/onnxruntime_qat_test.py
+[Acc. under onnxruntime]: https://github.com/torchpipe/torchpipe/blob/v0/examples/int8/qat/onnxruntime_qat_test.py

docusaurus.config.js

@@ -58,11 +58,11 @@ const config = {
           editUrl: ({locale, versionDocsDirPath, docPath}) => {
                   // Link to Crowdin for French docs
                   if (locale == 'en') { 
-                    return `https://github.com/torchpipe/torchpipe.github.io/edit/main/docs/${docPath}`;
+                    return `https://github.com/torchpipe/torchpipe.github.io/edit/v0/docs/${docPath}`;
                   }
                   // Link to GitHub for English docs
 
-                  return `https://github.com/torchpipe/torchpipe.github.io/edit/main/i18n/zh/docusaurus-plugin-content-docs/current/${docPath}`;
+                  return `https://github.com/torchpipe/torchpipe.github.io/edit/v0/i18n/zh/docusaurus-plugin-content-docs/current/${docPath}`;
                 },
           sidebarCollapsed: true,
           showLastUpdateTime:true,
@@ -192,7 +192,7 @@ const config = {
           //   label: "Nrwl",
           // },
           {
-            href: "https://github.com/torchpipe/torchpipe/",
+            href: "https://github.com/torchpipe/torchpipe/tree/v0",
             className: "header-github-link",
             "aria-label": "Github repository",
             position: "right",

i18n/zh/docusaurus-plugin-content-docs/current/backend-reference/torch.mdx

@@ -151,7 +151,7 @@ tensorrt推理引擎
 
 
 
-参见[示例](https://github.com/torchpipe/torchpipe/tree/main/examples/int8).
+参见[示例](https://github.com/torchpipe/torchpipe/tree/v0/examples/int8).
 
 
 ### 前向计算