[Frontend] Support configurable mm placeholder strings & flexible video sampling policies via CLI flags. (#20105)

Signed-off-by: Chenheli Hua <huachenheli@outlook.com>

tests/engine/test_arg_utils.py

@@ -231,6 +231,58 @@ def test_limit_mm_per_prompt_parser(arg, expected):
     assert args.limit_mm_per_prompt == expected
 
 
+@pytest.mark.parametrize(
+    ("arg", "expected"),
+    [
+        (None, dict()),
+        ('{"video": {"num_frames": 123} }', {
+            "video": {
+                "num_frames": 123
+            }
+        }),
+        (
+            '{"video": {"num_frames": 123, "fps": 1.0, "foo": "bar"}, "image": {"foo": "bar"} }',  # noqa
+            {
+                "video": {
+                    "num_frames": 123,
+                    "fps": 1.0,
+                    "foo": "bar"
+                },
+                "image": {
+                    "foo": "bar"
+                }
+            }),
+    ])
+def test_media_io_kwargs_parser(arg, expected):
+    parser = EngineArgs.add_cli_args(FlexibleArgumentParser())
+    if arg is None:
+        args = parser.parse_args([])
+    else:
+        args = parser.parse_args(["--media-io-kwargs", arg])
+
+    assert args.media_io_kwargs == expected
+
+
+@pytest.mark.parametrize(("arg", "expected"), [
+    (None, dict()),
+    ('{"video":"<|video_placeholder|>"}', {
+        "video": "<|video_placeholder|>"
+    }),
+    ('{"video":"<|video_placeholder|>", "image": "<|image_placeholder|>"}', {
+        "video": "<|video_placeholder|>",
+        "image": "<|image_placeholder|>"
+    }),
+])
+def test_mm_placeholder_str_override_parser(arg, expected):
+    parser = EngineArgs.add_cli_args(FlexibleArgumentParser())
+    if arg is None:
+        args = parser.parse_args([])
+    else:
+        args = parser.parse_args(["--mm-placeholder-str-override", arg])
+
+    assert args.mm_placeholder_str_override == expected
+
+
 def test_compilation_config():
     parser = EngineArgs.add_cli_args(FlexibleArgumentParser())