Skip to content

Fix faq/index and motivation/fluid links #7880#7885

Open
Letin147 wants to merge 3 commits intoPaddlePaddle:developfrom
Letin147:fix-links-issue7735
Open

Fix faq/index and motivation/fluid links #7880#7885
Letin147 wants to merge 3 commits intoPaddlePaddle:developfrom
Letin147:fix-links-issue7735

Conversation

@Letin147
Copy link
Copy Markdown

@Letin147 Letin147 commented Apr 1, 2026

修复内容

根据 Issue #7735 Task 25 和 Task 55,修复以下失效链接:

1. docs/design/motivation/fluid.md

问题:Yuang Yu 对应的链接 https://research.google.com/pubs/104812.html 返回 404

修复:删除该链接,保留人名

- Based on a conversation with [Yuang Yu](https://research.google.com/pubs/104812.html), it seems to be the case but this needs to be looked into in-depth.
+ Based on a conversation with Yuang Yu, it seems to be the case but this needs to be looked into in-depth.

### 2. docs/faq/index_cn.rst

问题:官网 API 文档链接指向首页而非 API 文档页

- 除此之外,你也可以查看 `官网 API 文档 <https://www.paddlepaddle.org.cn/documentation/docs/zh/index_cn.html>`_
+ 除此之外,你也可以查看 `官网 API 文档 <https://www.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html>`_

修复:修正链接指向正确的 API 文档页面

验证结果
✅ https://www.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html 可正常访问
⚠️ https://research.google.com/pubs/104812.html 返回 404(已删除链接)

Copilot AI review requested due to automatic review settings April 1, 2026 17:14
@paddle-bot
Copy link
Copy Markdown

paddle-bot bot commented Apr 1, 2026

感谢你贡献飞桨文档,文档预览构建中,Docs-New 跑完后即可预览,预览链接:http://preview-pr-7885.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html
预览工具的更多说明,请参考:飞桨文档预览工具

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

该 PR 依据 Issue #7735 的任务清单,修复文档中的失效/错误外链,提升文档可用性与可读性。

Changes:

  • 修正 FAQ 首页中“官网 API 文档”的外链地址,指向正确的 API 文档入口页。
  • 移除 fluid.md 中指向 Google Research 的已失效人物链接(保留人名引用)。
  • 额外替换 fluid.md 中 Movidius 的外链指向(PR 描述未覆盖)。

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File Description
docs/faq/index_cn.rst 将“官网 API 文档”链接从 guides 入口修正为 API 入口页
docs/design/motivation/fluid.md 移除已 404 的外部人物链接,并更新一处硬件厂商相关外链

本栏目以问答对的形式收录了用户开发过程中遇到的高频咨询类问题,包含了 2.0 版本的变化、安装、数据与数据处理、模型组网、训练、预测、模型保存与加载、参数调整、分布式等几类常见问题。

除此之外,你也可以查看 `官网 API 文档 <https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/index_cn.html>`_ 、 `历史 Issues <https://github.com/PaddlePaddle/Paddle/issues>`_ 、 `飞桨论坛 <https://aistudio.baidu.com/paddle/forum>`_ 来寻求解答。
除此之外,你也可以查看 `官网 API 文档 <https://www.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html>`_ 、 `历史 Issues <https://github.com/PaddlePaddle/Paddle/issues>`_ 、 `飞桨论坛 <https://aistudio.baidu.com/paddle/forum>`_ 来寻求解答。
Copy link

Copilot AI Apr 1, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PR 描述中提到原链接指向 .../zh/index_cn.html,但本次改动实际是从 .../zh/guides/index_cn.html 改为 .../zh/api/index_cn.html。建议同步更正 PR 描述里的旧链接,避免审阅者核对时产生歧义。

Copilot uses AI. Check for mistakes.
Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@copilot apply changes based on this feedback

## Backward Compatibility of Fluid

Given all the advantages from the removal of the concept of a *model*, hardware manufacturers might still prefer the existence of the concept of a model, so it would be easier for them to support multiple frameworks all at once and could run a trained model during inference. For example, Nervana, a startup company acquired by Intel, has been working on an XPU that reads the models in the format known as [n-graph](https://github.com/NervanaSystems/ngraph). Similarly, [Movidius](https://www.movidius.com/) is producing a mobile deep learning chip that reads and runs graphs of operators. The well-known [ONNX](https://github.com/onnx/onnx) is also a file format of graphs of operators. <!-- typos: disable-line -->
Given all the advantages from the removal of the concept of a *model*, hardware manufacturers might still prefer the existence of the concept of a model, so it would be easier for them to support multiple frameworks all at once and could run a trained model during inference. For example, Nervana, a startup company acquired by Intel, has been working on an XPU that reads the models in the format known as [n-graph](https://github.com/NervanaSystems/ngraph). Similarly, [Movidius](https://www.intel.com/content/www/us/en/developer/topic-technology/edge-5g/hardware/vision-accelerator-movidius-vpu.html) is producing a mobile deep learning chip that reads and runs graphs of operators. The well-known [ONNX](https://github.com/onnx/onnx) is also a file format of graphs of operators. <!-- typos: disable-line -->
Copy link

Copilot AI Apr 1, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

本文件中额外修改了 Movidius 的外部链接(从 www.movidius.com 换成 Intel 的页面),但 PR 描述未提及该变更。建议在 PR 描述中补充说明该链接同样失效/需要替换,或将此处改动拆分到单独的链接修复任务,避免范围不清。

Copilot uses AI. Check for mistakes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants