[Model]support qwen2_5_vl (#3557)

* adapt qwen_2_5_vl model

* adapt qwen_2_5_vl VIT model

* adapt qwen2_5_vl images_embeds

* adapt qwen2_5_vl 3D rope

* adapt qwen2_5_vl 3D rope v2

* adapt qwen2_5_vl processor

* adapt qwen2_5_vl bypass resampler_model

* adapt qwen2_5_vl 绕过部分ernie逻辑

* adapt qwen2_5_vl 绕过部分ernie逻辑 v2

* adapt qwen2_5_vl 权重加载与命名修改

* adapt qwen2_5_vl 非必须think_end_id

* adapt qwen2_5_vl 区分多种模型的extract_vision_features

* fix:adapt qwen2_5_vl model

* adapt qwen2_5_vl norm

* adapt qwen2_5_vl  processor 更新

* adapt qwen2_5_vl image and video success

* adapt qwen2_5_vl 部分整理代码

* adapt qwen2_5_vl 支持多卡

* adapt qwen2_5_vl on latest develop

* adapt qwen2_5_vl RL

* adapt qwen2_5_vl 整理代码

* support noex rope3d

* adapt qwen2_5_vl add init.py

* adapt qwen2_5_vl add init.py v2

* adapt qwen2_5_vl remove space

* adapt qwen2_5_vl remove space v2

* adapt qwen2_5_vl pre-commit

* adapt qwen2_5_vl update

* adapt qwen2_5_vl pre-commit v2

* adapt qwen2_5_vl modify comments

* adapt qwen2_5_vl fix indentation

* adapt qwen2_5_vl fix indentation v2

---------

Co-authored-by: wangyafeng <wangyafeng@baidu.com>
Co-authored-by: xiaoxiaohehe001 <49090790+xiaoxiaohehe001@users.noreply.github.com>
Co-authored-by: CSWYF3634076 <58356743+CSWYF3634076@users.noreply.github.com>

fastdeploy/multimodal/registry.py

@@ -20,7 +20,11 @@ class MultimodalRegistry:
     A registry for multimodal models
     """
 
-    mm_models: set[str] = {"Ernie4_5_VLMoeForConditionalGeneration", "Ernie5MoeForCausalLM"}
+    mm_models: set[str] = {
+        "Ernie4_5_VLMoeForConditionalGeneration",
+        "Ernie5MoeForCausalLM",
+        "Qwen2_5_VLForConditionalGeneration",
+    }
 
     @classmethod
     def contains_model(cls, name: str) -> bool: