[Model][VLM] Support Keye-VL-8B-Preview (#20126)

Signed-off-by: Kwai-Keye <Keye@kuaishou.com>

examples/offline_inference/vision_language.py

@@ -429,6 +429,37 @@ def run_internvl(questions: list[str], modality: str) -> ModelRequestData:
     )
 
 
+# Keye-VL
+def run_keye_vl(questions: list[str], modality: str) -> ModelRequestData:
+    model_name = "Kwai-Keye/Keye-VL-8B-Preview"
+
+    engine_args = EngineArgs(
+        model=model_name,
+        max_model_len=8192,
+        trust_remote_code=True,
+        limit_mm_per_prompt={modality: 1},
+    )
+
+    if modality == "image":
+        placeholder = "<|image_pad|>"
+    elif modality == "video":
+        placeholder = "<|video_pad|>"
+
+    prompts = [
+        (
+            f"<|im_start|>user\n<|vision_start|>{placeholder}<|vision_end|>"
+            f"{question}<|im_end|>\n"
+            "<|im_start|>assistant\n"
+        )
+        for question in questions
+    ]
+
+    return ModelRequestData(
+        engine_args=engine_args,
+        prompts=prompts,
+    )
+
+
 # Kimi-VL
 def run_kimi_vl(questions: list[str], modality: str) -> ModelRequestData:
     assert modality == "image"
@@ -1154,6 +1185,7 @@ model_example_map = {
     "h2ovl_chat": run_h2ovl,
     "idefics3": run_idefics3,
     "internvl_chat": run_internvl,
+    "keye_vl": run_keye_vl,
     "kimi_vl": run_kimi_vl,
     "llava": run_llava,
     "llava-next": run_llava_next,