[pull] main from mlc-ai:main

.github/workflows/build-site.yaml

@@ -16,6 +16,7 @@ jobs:
     - name: Configuring build Environment
       run: |
         sudo apt-get update
+        python -m pip install -U pip
 
     - name: Setup Ruby
       uses: ruby/setup-ruby@v1
@@ -24,13 +25,10 @@ jobs:
 
     - name: Installing dependencies
       run: |
+        python -m pip install -r docs/requirements.txt
         gem install jekyll jekyll-remote-theme jekyll-sass-converter
 
-    - name: Build site
-      run: |
-        cd site && jekyll b && cd ..
-
-    - name: Push to gh-pages branch
+    - name: Build and deploy site
       if: github.ref == 'refs/heads/main'
       run: |
         git remote set-url origin https://x-access-token:${{ secrets.MLC_GITHUB_TOKEN }}@github.com/$GITHUB_REPOSITORY

README.md

@@ -10,7 +10,7 @@
 **High-Performance In-Browser LLM Inference Engine.**
 
 
-[Get Started](#get-started) | [Blogpost](https://blog.mlc.ai/2024/06/13/webllm-a-high-performance-in-browser-llm-inference-engine) | [Examples](examples) | [Documentation](https://mlc.ai/mlc-llm/docs/deploy/webllm.html)
+[Documentation](https://webllm.mlc.ai/docs/) | [Blogpost](https://blog.mlc.ai/2024/06/13/webllm-a-high-performance-in-browser-llm-inference-engine) | [Paper](https://arxiv.org/abs/2412.15803) | [Examples](examples)
 
 </div>
 
@@ -455,6 +455,21 @@ This project is initiated by members from CMU Catalyst, UW SAMPL, SJTU, OctoML,
 
 This project is only possible thanks to the shoulders open-source ecosystems that we stand on. We want to thank the Apache TVM community and developers of the TVM Unity effort. The open-source ML community members made these models publicly available. PyTorch and Hugging Face communities make these models accessible. We would like to thank the teams behind Vicuna, SentencePiece, LLaMA, and Alpaca. We also would like to thank the WebAssembly, Emscripten, and WebGPU communities. Finally, thanks to Dawn and WebGPU developers.
 
+## Citation
+If you find this project to be useful, please cite:
+
+```
+@misc{ruan2024webllmhighperformanceinbrowserllm,
+      title={WebLLM: A High-Performance In-Browser LLM Inference Engine}, 
+      author={Charlie F. Ruan and Yucheng Qin and Xun Zhou and Ruihang Lai and Hongyi Jin and Yixin Dong and Bohan Hou and Meng-Shiun Yu and Yiyan Zhai and Sudeep Agarwal and Hangrui Cao and Siyuan Feng and Tianqi Chen},
+      year={2024},
+      eprint={2412.15803},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2412.15803}, 
+}
+```
+
 ## Contributors
 
 <a href="https://github.com/mlc-ai/web-llm/graphs/contributors">

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= python -m sphinx
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/README.md

@@ -0,0 +1,30 @@
+# WebLLM Documentation
+
+The documentation was built upon [Sphinx](https://www.sphinx-doc.org/en/master/).
+
+## Dependencies
+
+Run the following command in this directory to install dependencies first:
+
+```bash
+pip3 install -r requirements.txt
+```
+
+## Build the Documentation
+
+Then you can build the documentation by running:
+
+```bash
+make html
+```
+
+## View the Documentation
+
+Run the following command to start a simple HTTP server:
+
+```bash
+cd _build/html
+python3 -m http.server
+```
+
+Then you can view the documentation in your browser at `http://localhost:8000` (the port can be customized by appending ` -p PORT_NUMBER` in the python command above).

docs/conf.py

@@ -0,0 +1,102 @@
+# -*- coding: utf-8 -*-
+import os
+import sys
+
+import tlcpack_sphinx_addon
+
+# -- General configuration ------------------------------------------------
+
+sys.path.insert(0, os.path.abspath("../python"))
+sys.path.insert(0, os.path.abspath("../"))
+autodoc_mock_imports = ["torch"]
+
+# General information about the project.
+project = "web-llm"
+author = "WebLLM Contributors"
+copyright = "2023, %s" % author
+
+# Version information.
+
+version = "0.2.77"
+release = "0.2.77"
+
+extensions = [
+    "sphinx_tabs.tabs",
+    "sphinx_toolbox.collapse",
+    "sphinxcontrib.httpdomain",
+    "sphinx.ext.autodoc",
+    "sphinx.ext.napoleon",
+    "sphinx_reredirects",
+]
+
+redirects = {"get_started/try_out": "../index.html#getting-started"}
+
+source_suffix = [".rst"]
+
+language = "en"
+
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# A list of ignored prefixes for module index sorting.
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme is set by the make target
+import sphinx_rtd_theme
+
+html_theme = "sphinx_rtd_theme"
+html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+
+templates_path = []
+
+html_static_path = []
+
+footer_copyright = "© 2023 MLC LLM"
+footer_note = " "
+
+html_logo = "_static/img/mlc-logo-with-text-landscape.svg"
+
+html_theme_options = {
+    "logo_only": True,
+}
+
+header_links = [
+    ("Home", "https://webllm.mlc.ai/"),
+    ("GitHub", "https://github.com/mlc-ai/web-llm"),
+    ("Discord", "https://discord.gg/9Xpy2HGBuD"),
+]
+
+header_dropdown = {
+    "name": "Other Resources",
+    "items": [
+        ("WebLLM Chat", "https://chat.webllm.ai/"),
+        ("MLC Course", "https://mlc.ai/"),
+        ("MLC Blog", "https://blog.mlc.ai/"),
+        ("MLC LLM", "https://llm.mlc.ai/"),
+    ],
+}
+
+html_context = {
+    "footer_copyright": footer_copyright,
+    "footer_note": footer_note,
+    "header_links": header_links,
+    "header_dropdown": header_dropdown,
+    "display_github": True,
+    "github_user": "mlc-ai",
+    "github_repo": "web-llm",
+    "github_version": "main/docs/",
+    "theme_vcs_pageview_mode": "edit",
+    # "header_logo": "/path/to/logo",
+    # "header_logo_link": "",
+    # "version_selecter": "",
+}
+
+
+# add additional overrides
+templates_path += [tlcpack_sphinx_addon.get_templates_path()]
+html_static_path += [tlcpack_sphinx_addon.get_static_path()]

docs/developer/add_models.rst

@@ -0,0 +1,6 @@
+Adding Models
+=============
+
+WebLLM allows you to compile custom language models using `MLC LLM <https://llm.mlc.ai/>`_ and then serve compiled model through WebLLM.
+
+For instructions of how to compile and add custom models to WebLLM, check the `MLC LLM documentation here <https://llm.mlc.ai/docs/deploy/webllm.html>`_. 

docs/developer/building_from_source.rst

@@ -0,0 +1,35 @@
+Building From Source
+====================
+
+Clone the Repository
+---------------------
+.. code-block:: bash
+
+   git clone https://github.com/mlc-ai/web-llm.git
+   cd web-llm
+
+Install Dependencies
+---------------------
+.. code-block:: bash
+
+   npm install
+
+Build the Project
+-----------------
+.. code-block:: bash
+
+   npm run build
+
+Test Changes
+------------
+
+To test you changes, you can reuse any existing example or create a new example for your new functionality to test.
+
+Then, to test the effects of your code change in an example, inside ``examples/<example>/package.json``, change from ``"@mlc-ai/web-llm": "^0.2.xx"`` to ``"@mlc-ai/web-llm": ../...`` to let it reference you local code.
+
+.. code-block:: bash
+
+   cd examples/<example>
+   # Modify the package.json
+   npm install
+   npm start

docs/index.rst

@@ -0,0 +1,35 @@
+👋 Welcome to WebLLM
+====================
+
+`GitHub <https://github.com/mlc-ai/web-llm>`_ | `WebLLM Chat <https://chat.webllm.ai/>`_ | `NPM <https://www.npmjs.com/package/@mlc-ai/web-llm>`_ | `Discord <https://discord.gg/9Xpy2HGBuD>`_
+
+WebLLM is a high-performance in-browser language model inference engine that brings large language models (LLMs) to web browsers with hardware acceleration. With WebGPU support, it allows developers to build AI-powered applications directly within the browser environment, removing the need for server-side processing and ensuring privacy.
+
+It provides a specialized runtime for the web backend of MLCEngine, leverages
+`WebGPU <https://www.w3.org/TR/webgpu/>`_ for local acceleration, offers OpenAI-compatible API,
+and provides built-in support for web workers to separate heavy computation from the UI flow.
+
+Key Features
+------------
+- 🌐 In-Browser Inference: Run LLMs directly in the browser
+- 🚀 WebGPU Acceleration: Leverage hardware acceleration for optimal performance
+- 🔄 OpenAI API Compatibility: Seamless integration with standard AI workflows
+- 📦 Multiple Model Support: Works with Llama, Phi, Gemma, Mistral, and more
+
+Start exploring WebLLM by `chatting with WebLLM Chat <https://chat.webllm.ai/>`_, and start building webapps with high-performance local LLM inference with the following guides and tutorials.
+
+.. toctree::
+   :maxdepth: 2
+   :caption: User Guide
+
+   user/get_started.rst
+   user/basic_usage.rst
+   user/advanced_usage.rst
+   user/api_reference.rst
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Developer Guide
+
+   developer/building_from_source.rst
+   developer/add_models.rst

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/requirements.txt

@@ -0,0 +1,8 @@
+sphinx-tabs == 3.4.1
+sphinx-rtd-theme
+sphinx == 5.2.3
+sphinx-toolbox == 3.4.0
+tlcpack-sphinx-addon==0.2.2
+sphinxcontrib_httpdomain==1.8.1
+sphinxcontrib-napoleon==0.7
+sphinx-reredirects==0.1.2