[Doc] [1/N] Initial guide for merged multi-modal processor (vllm-proj…

…ect#11925) Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
neuralmagic · Jan 10, 2025 · 12664dd · 12664dd
1 parent 241ad7b
commit 12664dd
Show file tree

Hide file tree

Showing 19 changed files with 403 additions and 168 deletions.
diff --git a/docs/requirements-docs.txt b/docs/requirements-docs.txt
@@ -3,6 +3,7 @@ sphinx-book-theme==1.0.1
 sphinx-copybutton==0.5.2
 myst-parser==3.0.1
 sphinx-argparse==0.4.0
+sphinx-design==0.6.1
 sphinx-togglebutton==0.3.2
 msgspec
 cloudpickle

diff --git a/docs/source/api/multimodal/index.md b/docs/source/api/multimodal/index.md
@@ -7,7 +7,7 @@ vLLM provides experimental support for multi-modal models through the {mod}`vllm
 Multi-modal inputs can be passed alongside text and token prompts to [supported models](#supported-mm-models)
 via the `multi_modal_data` field in {class}`vllm.inputs.PromptType`.
 
-Looking to add your own multi-modal model? Please follow the instructions listed [here](#enabling-multimodal-inputs).
+Looking to add your own multi-modal model? Please follow the instructions listed [here](#supports-multimodal).
 
 ## Module Contents
 

diff --git a/docs/source/api/multimodal/inputs.md b/docs/source/api/multimodal/inputs.md
@@ -3,7 +3,7 @@
 ## User-facing inputs
 
 ```{eval-rst}
-.. autodata:: vllm.multimodal.MultiModalDataDict
+.. autodata:: vllm.multimodal.inputs.MultiModalDataDict
 ```
 
 ## Internal data structures

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -43,6 +43,7 @@
     "sphinx.ext.autosummary",
     "myst_parser",
     "sphinxarg.ext",
+    "sphinx_design",
     "sphinx_togglebutton",
 ]
 myst_enable_extensions = [

diff --git a/docs/source/contributing/model/index.md b/docs/source/contributing/model/index.md
@@ -2,7 +2,7 @@
 
 # Adding a New Model
 
-This section provides more information on how to integrate a [HuggingFace Transformers](https://github.com/huggingface/transformers) model into vLLM.
+This section provides more information on how to integrate a [PyTorch](https://pytorch.org/) model into vLLM.
 
 ```{toctree}
 :caption: Contents