biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[VLM] Support caching in merged multi-modal processor (#11396)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-28 01:22:48 +08:00
committed by GitHub
parent 5ce4627a7e
commit 101418096f
20 changed files with 1459 additions and 452 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
docs/source/design/multimodal/multimodal_index.md
View File

@@ -45,31 +45,23 @@ adding_multimodal_plugin
### Base Classes
```{eval-rst}
.. autodata:: vllm.multimodal.NestedTensors
```
```{eval-rst}
.. autodata:: vllm.multimodal.BatchedTensorInputs
```
```{eval-rst}
.. autoclass:: vllm.multimodal.MultiModalDataBuiltins
.. automodule:: vllm.multimodal.base
:members:
:show-inheritance:
```
```{eval-rst}
.. autodata:: vllm.multimodal.MultiModalDataDict
```
### Input Classes
```{eval-rst}
.. autoclass:: vllm.multimodal.MultiModalKwargs
.. automodule:: vllm.multimodal.inputs
:members:
:show-inheritance:
```
### Audio Classes
```{eval-rst}
.. autoclass:: vllm.multimodal.MultiModalPlugin
.. automodule:: vllm.multimodal.audio
:members:
:show-inheritance:
```
@@ -81,3 +73,11 @@ adding_multimodal_plugin
:members:
:show-inheritance:
```
### Video Classes
```{eval-rst}
.. automodule:: vllm.multimodal.video
:members:
:show-inheritance:
```