[Model] support new model ovis2.5 (#23084)

Signed-off-by: myselvess <244285088@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

examples/offline_inference/vision_language.py

@@ -1105,6 +1105,38 @@ def run_ovis(questions: list[str], modality: str) -> ModelRequestData:
     )
 
 
+# Ovis2_5
+def run_ovis2_5(questions: list[str], modality: str) -> ModelRequestData:
+    model_name = "AIDC-AI/Ovis2.5-2B"
+
+    engine_args = EngineArgs(
+        model=model_name,
+        max_model_len=4096,
+        max_num_seqs=2,
+        trust_remote_code=True,
+        dtype="half",
+        limit_mm_per_prompt={modality: 1},
+    )
+    if modality == "image":
+        placeholder = "<image>"
+    elif modality == "video":
+        placeholder = "<video>"
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+    messages = [
+        [{"role": "user", "content": f"{placeholder}\n{question}"}]
+        for question in questions
+    ]
+    prompts = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+    return ModelRequestData(
+        engine_args=engine_args,
+        prompts=prompts,
+    )
+
+
 # PaliGemma
 def run_paligemma(questions: list[str], modality: str) -> ModelRequestData:
     assert modality == "image"
@@ -1579,6 +1611,7 @@ model_example_map = {
     "nemotron_vl": run_nemotron_vl,
     "NVLM_D": run_nvlm_d,
     "ovis": run_ovis,
+    "ovis2_5": run_ovis2_5,
     "paligemma": run_paligemma,
     "paligemma2": run_paligemma2,
     "phi3_v": run_phi3v,