[Model] Initialize support for Deepseek-VL2 models (#11578)

Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

docs/source/models/supported_models.md

@@ -610,6 +610,13 @@ See [this page](#generative-models) for more information on how to use generativ
   -
   - ✅︎
   - ✅︎
+* - `DeepseekVLV2ForCausalLM`
+  - DeepSeek-VL2
+  - T + I<sup>+</sup>
+  - `deepseek-ai/deepseek-vl2-tiny`(WIP), `deepseek-ai/deepseek-vl2-small`, `deepseek-ai/deepseek-vl2` etc. (see note)
+  -
+  - ✅︎
+  - ✅︎
 * - `FuyuForCausalLM`
   - Fuyu
   - T + I
@@ -755,8 +762,19 @@ See [this page](#generative-models) for more information on how to use generativ
 <sup>E</sup> Pre-computed embeddings can be inputted for this modality.  
 <sup>+</sup> Multiple items can be inputted per text prompt for this modality.
 
+````{note}
+The `deepseek-ai/deepseek-vl2-tiny` is not supported yet.
+
+To use `DeepSeek-VL2` series models, you need to install a fork version `deepseek_vl2` package:
+```shell
+pip install git+https://github.com/Isotr0py/DeepSeek-VL2.git
+```
+
+Besides, to run `DeepSeek-VL2` series models, you have to pass `--hf_overrides '{"architectures": ["DeepseekVLV2ForCausalLM"]}'` when running vLLM.
+````
+
 ```{note}
-To use `TIGER-Lab/Mantis-8B-siglip-llama3`, you have pass `--hf_overrides '{"architectures": ["MantisForConditionalGeneration"]}'` when running vLLM.
+To use `TIGER-Lab/Mantis-8B-siglip-llama3`, you have to pass `--hf_overrides '{"architectures": ["MantisForConditionalGeneration"]}'` when running vLLM.
 ```
 
 ```{note}