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

3
docs/source/models/supported_models.md
View File

@@ -755,8 +755,7 @@ vLLM currently only supports adding LoRA to the language backbone of multimodal
```
```{note}
To use {code}`TIGER-Lab/Mantis-8B-siglip-llama3`, you have to install their GitHub repo ({code}`pip install git+https://github.com/TIGER-AI-Lab/Mantis.git`)
and pass {code}`--hf_overrides '{"architectures": ["MantisForConditionalGeneration"]}'` when running vLLM.
To use {code}`TIGER-Lab/Mantis-8B-siglip-llama3`, you have pass {code}`--hf_overrides '{"architectures": ["MantisForConditionalGeneration"]}'` when running vLLM.
```
```{note}