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

[Doc] [1/N] Initial guide for merged multi-modal processor (#11925)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-01-10 22:30:25 +08:00
committed by GitHub
parent 241ad7b301
commit 12664ddda5
19 changed files with 433 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/serving/multimodal_inputs.md
View File

@@ -14,7 +14,7 @@ and [open an issue on GitHub](https://github.com/vllm-project/vllm/issues/new/ch
To input multi-modal data, follow this schema in {class}`vllm.inputs.PromptType`:
- `prompt`: The prompt should follow the format that is documented on HuggingFace.
- `multi_modal_data`: This is a dictionary that follows the schema defined in {class}`vllm.multimodal.MultiModalDataDict`.
- `multi_modal_data`: This is a dictionary that follows the schema defined in {class}`vllm.multimodal.inputs.MultiModalDataDict`.
### Image