Implicit language-model-only mode via limit-mm-per-prompt (#22299)

Signed-off-by: Roger Wang <hey@rogerw.me>
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: XIn Li <xinli@nvidia.com>
Signed-off-by: Junhao Li <junhao@ubicloud.com>
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Signed-off-by: Linkun <github@lkchen.net>
Co-authored-by: Ning Xie <andy.xning@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Zhiyu <zhiyuc@nvidia.com>
Co-authored-by: Shu Wang <shuw@nvidia.com>
Co-authored-by: XIn Li <xinli@nvidia.com>
Co-authored-by: Junhao Li <streaver91@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Yuxuan Zhang <2448370773@qq.com>
Co-authored-by: ZiTian Zhao <zitian.zhao@tencentmusic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
Co-authored-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Hong Hanh <hanh.usth@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: lkchen <github@lkchen.net>

tests/multimodal/test_registry.py

@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""
+Unit tests for MultiModalRegistry.supports_multimodal_inputs and
+Qwen2.5-VL visual component loading behavior.
+"""
+
+import pytest
+
+from vllm.multimodal import MULTIMODAL_REGISTRY
+
+from ..models.utils import build_model_context
+
+
+@pytest.mark.parametrize(
+    "model_id,limit_mm_per_prompt,expected",
+    [
+        ("Qwen/Qwen2-0.5B-Instruct", {}, False),
+        ("Qwen/Qwen2.5-VL-3B-Instruct", {}, True),
+        ("Qwen/Qwen2.5-VL-3B-Instruct", {
+            "image": 0,
+            "video": 0
+        }, False),
+        ("Qwen/Qwen2.5-VL-3B-Instruct", {
+            "image": 0
+        }, True),
+    ],
+)
+@pytest.mark.core_model
+def test_supports_multimodal_inputs(model_id, limit_mm_per_prompt, expected):
+    """Test supports_multimodal_inputs returns correct boolean for various 
+    configs."""
+    ctx = build_model_context(
+        model_id,
+        limit_mm_per_prompt=limit_mm_per_prompt,
+    )
+    assert MULTIMODAL_REGISTRY.supports_multimodal_inputs(
+        ctx.model_config) is expected