update README & docs #404
update README & docs #404
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @Harahan, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request focuses on a comprehensive overhaul of the project's documentation, aiming to enhance readability, maintainability, and visual consistency across all language versions of the README files and the Sphinx-generated documentation. The changes improve the user experience by standardizing formatting, updating the documentation theme, and refining build dependencies.
Highlights
- Standardized README Formatting: I've updated the
README.md,README_ja.md, andREADME_zh.mdfiles to standardize their visual presentation. This includes changing main titles to HTML<h1>tags for better styling, adding consistent emojis to section headings (e.g., 'Latest News', 'Usage', 'Supported Models'), and collapsing long lists (like supported models, algorithms, and acknowledgments) into collapsible<details>sections to improve readability and reduce initial page clutter. - Sphinx Documentation Theme Update: The Sphinx documentation build configuration files (
docs/en/source/conf.pyanddocs/zh_cn/source/conf.py) have been updated. This migrates the documentation theme fromtrojanzoo_sphinx_themeto the more modern and feature-richsphinx_book_theme. Associated theme options, extensions, and path configurations have been adjusted to ensure compatibility and leverage the new theme's capabilities, including improved autodoc handling for mocked imports. - Documentation Dependencies Refinement: The
requirements/docs.txtfile has been updated to reflect the new Sphinx theme and related documentation tools. Outdated or unused dependencies have been removed, and new ones, such assphinx-book-theme,sphinx-argparse,sphinxcontrib.redoc, andsphinxcontrib.openapi, have been added with specific versioning to ensure a stable and consistent documentation build environment. - Citation Information Update: The citation sections across all
READMEfiles have been streamlined to feature a single, standardized EMNLP conference paper entry, providing a more concise and accurate reference for the project's academic contributions.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
| @@ -11,7 +10,7 @@ | |||
| [](https://discord.com/invite/NfJzbkK3jY) | |||
| [](http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=I9IGPWWj8uuRXWH3_ELWjouf6gkIMgUl&authKey=GA3WbFAsm90ePJf%2FCbc7ZyXXq4ShQktlBaLxgqS5yuSPAsr3%2BDKMRdosUiLYoilO&noverify=0&group_code=526192592) | |||
| [](https://llmc-en.readthedocs.io/en/latest/) | |||
| [](https://llmc-zhcn.readthedocs.io/en/latest/) | |||
| [](https://llmc-zhcn.readthedocs.io/en/latest/)  | |||
There was a problem hiding this comment.
The Japanese documentation badge (ドキュメント-日本語) incorrectly links to the Chinese documentation (https://llmc-zhcn.readthedocs.io/en/latest/). This appears to be a copy-paste error. Please update the link to point to the correct Japanese documentation. If Japanese docs are not yet available, it might be better to remove this badge temporarily to avoid confusing users.
|
|
||
| - **Nov 20, 2024:** 🔥 We now fully support the quantization of ✨`DeepSeekv2(2.5)` and other `MOE` models, as well as ✨`Qwen2VL`, `Llama3.2`, and other `VLM` models. Supported quantization methods include ✅integer quantization, ✅floating-point quantization, and advanced algorithms like ✅AWQ, ✅GPTQ, ✅SmoothQuant, and ✅Quarot. | ||
|
|
||
| - **Nov 12, 2024:** 🔥 We have added support for 💥`static per-tensor activation quantization` across various models and algorithms, covering ✅integer quantization and ✅floating-point quantization to further optimize performance and efficiency. Additionally, we now support exporting ✨`real quantized models` and using the [VLLM](https://github.com/vllm-project/vllm) and [SGLang](https://github.com/sgl-project/sglang) backends for inference acceleration. For more details, refer to the [VLLM documentation](https://llmc-en.readthedocs.io/en/latest/backend/vllm.html) and [SGLang documentation](https://llmc-en.readthedocs.io/en/latest/backend/sglang.html). | ||
|
|
||
| - **Sep 26, 2024:** 🔥 We now support exporting 💥`FP8 quantized(E4M3, E5M2)` models from 🚀`LLMC` to advanced inference backends such as [VLLM](https://github.com/vllm-project/vllm) and [SGLang](https://github.com/sgl-project/sglang). For detailed usage, please refer to the [VLLM documentation](https://llmc-en.readthedocs.io/en/latest/backend/vllm.html) and [SGLang documentation](https://llmc-en.readthedocs.io/en/latest/backend/sglang.html). | ||
|
|
||
| <details close> |
There was a problem hiding this comment.
The close attribute on the <details> tag is non-standard HTML. To make a <details> element collapsed by default, you should simply omit the close attribute. Using <details> is the standard-compliant way and ensures compatibility across different Markdown renderers.
| <details close> | |
| <details> |
| @@ -49,6 +42,9 @@ docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/llmcompression:pure-lates | |||
|
|
|||
| - **2024年9月26日:** 🔥 `LLMC`からの✨ `FP8量子化（E4M3、E5M2）`モデルを、VLLMやSGLangのような高度な推理バックエンドにエクスポートできるようになりました。🚀 詳細な使用方法については、[VLLMのドキュメント](https://llmc-en.readthedocs.io/en/latest/backend/vllm.html)と[SGLangのドキュメント](https://llmc-en.readthedocs.io/en/latest/backend/sglang.html)を参照してください。 | |||
|
|
|||
| <details close> | |||
There was a problem hiding this comment.
The close attribute for the <details> tag is non-standard HTML. The standard way to have a collapsed section is to just use <details>. This will improve compatibility across different Markdown renderers and maintain consistency with other sections.
| <details close> | |
| <details> |
| @@ -49,6 +42,9 @@ docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/llmcompression:pure-lates | |||
|
|
|||
| - **2024年9月26日:** 🔥 我们现在支持从🚀 `LLMC`导出💥 `FP8 量化（E4M3，E5M2）`模型到一些先进的推理后端，例如[VLLM](https://github.com/vllm-project/vllm)和[SGLang](https://github.com/sgl-project/sglang)。关于详细使用方法，请参阅[VLLM文档](https://llmc-zhcn.readthedocs.io/en/latest/backend/vllm.html)和[SGLang文档](https://llmc-zhcn.readthedocs.io/en/latest/backend/sglang.html)。 | |||
|
|
|||
| <details close> | |||
There was a problem hiding this comment.
The close attribute for the <details> tag is non-standard HTML. To create a collapsed section that is compatible with all Markdown renderers, the standard is to use <details> without any attributes. This will ensure it works correctly everywhere and is consistent with other collapsible sections in the file.
| <details close> | |
| <details> |
No description provided.