gitlab -> github

tp-nan · tp-nan · commit 1a08f9e3fbf1 · 2023-10-24T19:46:41.000+08:00
diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 
 
 <p align="center">
-<h1 align="center">Documentation for torchpipe</h1>
+<h1 align="center">Documentation for [torchpipe](https://github.com/torchpipe/torchpipe)</h1>
 <h6 align="center">Accelerated <a href="https://pytorch.org/">Pytorch</a> Serving with Multithreading</h6>
 </p>
 <p align="center">
@@ -23,9 +23,9 @@ Torchpipe is a multi-instance pipeline parallel library that acts as a bridge be
 
 
 
-torchpipe代码正在开源准备中。这里是其文档站点
+这里是其文档站点
 
-The torchpipe code is being prepared for open sourcing. Here is its documentation site.
+Here is its documentation site.
 
 
 
diff --git a/docs/backend-reference/torch.mdx b/docs/backend-reference/torch.mdx
@@ -138,7 +138,7 @@ For quantizing onnx models using tensorrt, the following parameters are availabl
 
 
 
-See [example](https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/int8). 
+See [example](https://github.com/torchpipe/torchpipe/-/tree/master/examples/int8). 
 
 
 ### Forward Computation
diff --git a/docs/benchmark.mdx b/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://g.hz.netease.com/deploy/torchpipe/blob/main/libs/commands/import/README.md
+[import]: https://github.com/torchpipe/torchpipe/blob/main/libs/commands/import/README.md
 
  
 
diff --git a/docs/contribution_guide/communicate.md b/docs/contribution_guide/communicate.md
@@ -4,7 +4,7 @@ title:  Communication and Questions
 type: reference
 ---
 
-Please submit an [issue](https://g.hz.netease.com/deploy/torchpipe/-/issues) here.
+Please submit an [issue](https://github.com/torchpipe/torchpipe/-/issues) here.
 
 # Communication
 POPO communication group: Group ID: 4101019
diff --git a/docs/contribution_guide/modify_the_code.md b/docs/contribution_guide/modify_the_code.md
@@ -25,8 +25,8 @@ pip install -r requirements.txt
 pytest .
 ```
 
-If necessary, please consider supplementing with [Python tests](https://g.hz.netease.com/deploy/torchpipe/-/tree/develop/test).
+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://g.hz.netease.com/deploy/torchpipe/-/blob/develop/.clang-format).
+Please configure a formatting plugin to enable [.clang-format](https://github.com/torchpipe/torchpipe/-/blob/develop/.clang-format).
 :::
diff --git a/docs/current_state.mdx b/docs/current_state.mdx
@@ -39,7 +39,7 @@
 | 编译                         | NGC docker/定制docker  | A                                          | -         |
 |                              | c++扩展                | A                                          | -         |
 |                              | pypi/manylinux         | B                                          | -         |
-|                              | 文档CI管道             | A(gitlab CI走通，开源后自动更新到github.io) | -         |
+|                              | 文档CI管道             | A(github.io) | -         |
 | 规范                         | 第三方代码的引用       | C                                          | -         |
 |                              | license                | C                                          | -         |
 |                              | 代码规范               | B                                          | -         |
diff --git a/docs/installation.mdx b/docs/installation.mdx
@@ -33,7 +33,7 @@ First, clone the code:
 
 ```bash
 git clone -b master ssh://git@g.hz.netease.com:22222/deploy/torchpipe.git
-# git clone -b master https://g.hz.netease.com/deploy/torchpipe.git
+# git clone -b master https://github.com/torchpipe/torchpipe.git
 cd torchpipe/ && git submodule update --init --recursive
 ```
 
@@ -144,7 +144,7 @@ For more examples, see [Showcase](./showcase/showcase.mdx).
 
 ## Customizing Dockerfile {#selfdocker}
 
-Refer to the [example Dockerfile](https://g.hz.netease.com/deploy/torchpipe/-/blob/master/docker/torchpipe.base). After downloading TensorRT and OpenCV in advance, you can compile the corresponding base image.
+Refer to the [example Dockerfile](https://github.com/torchpipe/torchpipe/-/blob/master/docker/torchpipe.base). After downloading TensorRT and OpenCV in advance, you can compile the corresponding base image.
 ```
 # put TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-11.8.tar.gz into thirdparty/
 wget https://codeload.github.com/opencv/opencv/zip/refs/tags/4.5.4 -O thirdparty/opencv-4.5.4.zip
diff --git a/docs/python/test.mdx b/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://g.hz.netease.com/deploy/torchpipe/-/blob/master/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/master/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.
 
diff --git a/docs/quick_start_new_user.md b/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://g.hz.netease.com/deploy/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/develop/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://g.hz.netease.com/deploy/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/develop/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://g.hz.netease.com/deploy/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/develop/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://g.hz.netease.com/deploy/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/develop/examples/resnet50_thrift/client_qps.py)
 
 With the same Thrift service interface, testing on a machine with NIDIA-3080 GPU, 36-core CPU, and concurrency of 10, we have the following results:
 
diff --git a/docs/showcase/showcase.mdx b/docs/showcase/showcase.mdx
@@ -15,10 +15,10 @@ slug: /showcase
 |        [PP-OCRv2]        | ![](../assets/ppocr.svg)               | [MapReduce](../Inter-node/graphtraversal.mdx#mapreduce)<br />[Jump]                                       |      |
 | [tensorrt's native int8] |                                        | [TensorrtTensor](../backend-reference/torch.mdx#tensorrttensor)                                           |      |
 
-[resnet18]: https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/resnet18
-[yolox]: https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/yolox
-[PP-OCRv2]: https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/ppocr
-[TensorRT's native INT8]: https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/int8
+[resnet18]: https://github.com/torchpipe/torchpipe/-/tree/master/examples/resnet18
+[yolox]: https://github.com/torchpipe/torchpipe/-/tree/master/examples/yolox
+[PP-OCRv2]: https://github.com/torchpipe/torchpipe/-/tree/master/examples/ppocr
+[TensorRT's native INT8]: https://github.com/torchpipe/torchpipe/-/tree/master/examples/int8
 
 [torchpipe.utils.cpp_extension.load]: ../python/compile.mdx
 [filter]: ../Inter-node/filter.mdx
diff --git a/docs/tools/quantization.mdx b/docs/tools/quantization.mdx
@@ -11,7 +11,7 @@ The post-training quantization process of TensorRT mainly includes two steps:
 - Prepare quantization data, about 500 pieces. We will save the data in PyTorch format in the backend.
 - Launch the quantization process with the prepared data and generate the model.
 
-For more details, please refer to the [example](https://g.hz.netease.com/deploy/torchpipe/-/tree/develop/examples/int8/README_en.md).
+For more details, please refer to the [example](https://github.com/torchpipe/torchpipe//examples/int8/README_en.md).
 
 ## Training-based Quantization (based on pytorch_quantization)
 In the [official notebook](https://github.com/NVIDIA/TensorRT/blob/release/8.6/quickstart/quantization_tutorial/qat-ptq-workflow.ipynb), NVIDIA summarizes how to improve quantization accuracy through training-based quantization in PyTorch.
@@ -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://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/calib_tools.py) for reference.
+We have integrated [calib_tools](https://github.com/torchpipe/torchpipe/-/blob/develop/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://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/download_data.py)
-- Train for 10 epochs to obtain the resnet50 model: [code](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/fp32_train.py), accuracy 98.44%
-- (optional) PyTorch ptq: [code](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/ptq.py), accuracy 96.64% (max)
-- (optional) PyTorch qat: [code](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/qat.py), accuracy 98.26%.
+- 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%.
 
 #### 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://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/ptq_merge_residual.py), accuracy 94.34% (mse)
-- qat: [code](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/qat_merge_residual.py), accuracy 95.82%.
+- 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%.
 
 
 #### 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://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/export_onnx_merge_residual.py)
-- Load fp32-onnx with TorchPipe and perform ptq: [code](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/torchpipe_ptq_test.py)
-- Test with qat-onnx loaded with TorchPipe: [code](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/torchpipe_qat_test.py)
+- 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)
 
 
 | 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://g.hz.netease.com/deploy/torchpipe/-/blob/develop/examples/int8/qat/onnxruntime_qat_test.py
+[Acc. under onnxruntime]: https://github.com/torchpipe/torchpipe/-/blob/develop/examples/int8/qat/onnxruntime_qat_test.py
diff --git a/docusaurus.config.js b/docusaurus.config.js
@@ -107,7 +107,7 @@ const config = {
         {
           name: "description",
           content:
-            "Accelerated PyTorch Serving with Multithreading.",
+            "Multi-thread Serving with PyTorch Frontend.",
         },
         { name: "og:image", content: "__.png" },
       ],
@@ -192,8 +192,8 @@ const config = {
           //   label: "Nrwl",
           // },
           {
-            href: "https://g.hz.netease.com/deploy/torchpipe/-/tree/develop",
-            className: "header-gitlab-link",
+            href: "https://github.com/torchpipe/torchpipe/",
+            className: "header-github-link",
             "aria-label": "Github repository",
             position: "right",
             title: "torchpipe on Github",
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/backend-reference/torch.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/backend-reference/torch.mdx
@@ -140,7 +140,7 @@ tensorrt推理引擎
 
 
 
-参见[示例](https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/int8).
+参见[示例](https://github.com/torchpipe/torchpipe/-/tree/master/examples/int8).
 
 
 ### 前向计算
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/benchmark.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/benchmark.mdx
@@ -77,7 +77,7 @@ thrift采用了多线程模式, 以`python`为客户端/服务端语言。
 |    triton-cli     | QPS: 15039 <br />   | -                  |
 
  
-[import]: https://g.hz.netease.com/deploy/torchpipe/blob/main/libs/commands/import/README.md
+[import]: https://github.com/torchpipe/torchpipe/blob/main/libs/commands/import/README.md
 
  
 
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/contribution_guide/communicate.md b/i18n/zh/docusaurus-plugin-content-docs/current/contribution_guide/communicate.md
@@ -4,7 +4,7 @@ title:  交流提问
 type: reference
 ---
 
-请在此提交[issue](https://g.hz.netease.com/deploy/torchpipe/-/issues)
+请在此提交[issue](https://github.com/torchpipe/torchpipe/-/issues)
 
 # 交流
 POPO交流群：群号：4101019
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/contribution_guide/modify_the_code.md b/i18n/zh/docusaurus-plugin-content-docs/current/contribution_guide/modify_the_code.md
@@ -25,8 +25,8 @@ pip install -r requirements.txt
 pytest .
 ```
 
-需要时请考虑补充[python测试](https://g.hz.netease.com/deploy/torchpipe/-/tree/develop/test)。
+需要时请考虑补充[python测试](https://github.com/torchpipe/torchpipe//test)。
 
 :::note 代码格式（optinal）
-请配置格式化插件以便[.clang-format](https://g.hz.netease.com/deploy/torchpipe/-/blob/develop/.clang-format)生效。
+请配置格式化插件以便[.clang-format](https://github.com/torchpipe/torchpipe/-/blob/develop/.clang-format)生效。
 :::
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/current_state.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/current_state.mdx
@@ -39,7 +39,7 @@
 | 编译                         | NGC docker/定制docker  | A                                          | -         |
 |                              | c++扩展                | A                                          | -         |
 |                              | pypi/manylinux         | B                                          | -         |
-|                              | 文档CI管道             | A(gitlab CI走通，开源后自动更新到github.io) | -         |
+|                              | 文档CI管道             | A(github.io) | -         |
 | 规范                         | 第三方代码的引用       | C                                          | -         |
 |                              | license                | C                                          | -         |
 |                              | 代码规范               | B                                          | -         |
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/installation.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/installation.mdx
@@ -32,7 +32,7 @@ type: explainer
 
 ```bash
 git clone -b master ssh://git@g.hz.netease.com:22222/deploy/torchpipe.git
-# git clone -b master https://g.hz.netease.com/deploy/torchpipe.git
+# git clone -b master https://github.com/torchpipe/torchpipe.git
 cd torchpipe/ && git submodule update --init --recursive
 ```
 
@@ -133,7 +133,7 @@ print(input["result"].shape)  # 失败则此键值一定不存在，即使输入
 
 ## 自定义dockerfile {#selfdocker}
 
-参考[示例dockerfile](https://g.hz.netease.com/deploy/torchpipe/-/blob/master/docker/torchpipe.base)，预先下载tensorrt和opencv后可编译相关基础镜像。
+参考[示例dockerfile](https://github.com/torchpipe/torchpipe/-/blob/master/docker/torchpipe.base)，预先下载tensorrt和opencv后可编译相关基础镜像。
 ```
 # put TensorRT-8.6.1.6.Linux.x86_64-gnu.cuda-11.8.tar.gz into thirdparty/
 wget https://codeload.github.com/opencv/opencv/zip/refs/tags/4.5.4 -O thirdparty/opencv-4.5.4.zip
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/python/test.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/python/test.mdx
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/quick_start_new_user.md b/i18n/zh/docusaurus-plugin-content-docs/current/quick_start_new_user.md
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/showcase/showcase.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/showcase/showcase.mdx
diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/tools/quantization.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/tools/quantization.mdx
diff --git a/i18n/zh/docusaurus-theme-classic/footer.json b/i18n/zh/docusaurus-theme-classic/footer.json
diff --git a/src/components/face-page.tsx b/src/components/face-page.tsx
diff --git a/src/data/members.data.ts b/src/data/members.data.ts

Original file line number	Diff line number	Diff line change
`@@ -138,7 +138,7 @@ For quantizing onnx models using tensorrt, the following parameters are availabl`
`138`	`138`
`139`	`139`
`140`	`140`
`141`		`-See [example](https://g.hz.netease.com/deploy/torchpipe/-/tree/master/examples/int8).`
	`141`	`+See [example](https://github.com/torchpipe/torchpipe/-/tree/master/examples/int8).`
`142`	`142`
`143`	`143`
`144`	`144`	`### Forward Computation`
Original file line number	Diff line number	Diff line change
`@@ -67,7 +67,7 @@ Client 10/Compute Backend Instance 1/Timeout 0/Max Batch 1`
`67`	`67`	`\| triton-cli \| QPS: 15039 <br /> \| - \|`
`68`	`68`
`69`	`69`
`70`		`-[import]: https://g.hz.netease.com/deploy/torchpipe/blob/main/libs/commands/import/README.md`
	`70`	`+[import]: https://github.com/torchpipe/torchpipe/blob/main/libs/commands/import/README.md`
`71`	`71`
`72`	`72`
`73`	`73`