[Enhancement] Add mm_encoder_only parameter and deprecation warning for convert option

- Introduced mm_encoder_only parameter to OmniModelConfig.
- Added a deprecation warning for the `--convert mm_encoder_only` option, advising users to switch to `--mm-encoder-only`.

Signed-off-by: [Your Name] <your.email@example.com>

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

vllm_omni/config/model.py

@@ -110,6 +110,7 @@ class OmniModelConfig(ModelConfig):
         mm_processor_cache_gb: float | None,
         mm_processor_cache_type: MMCacheType | None,
         mm_shm_cache_max_object_size_mb: int | None,
+        mm_encoder_only: bool | None,
         mm_encoder_tp_mode: MMEncoderTPMode | None,
         mm_encoder_attn_backend: AttentionBackendEnum | str | None,
         interleave_mm_strings: bool | None,
@@ -181,6 +182,15 @@ class OmniModelConfig(ModelConfig):
         )
         self.model_arch_config = self.get_model_arch_config()
 
+        if self.convert == "mm_encoder_only":
+            logger.warning_once(
+                "`--convert mm_encoder_only` is deprecated and "
+                "will be removed in v0.15. "
+                "Please use --mm-encoder-only` instead."
+            )
+            mm_encoder_only = True
+            self.convert = "none"
+
         architectures = self.architectures
         registry = self.registry
         is_generative_model = registry.is_text_generation_model(architectures, self)
@@ -262,6 +272,7 @@ class OmniModelConfig(ModelConfig):
                 mm_processor_cache_gb=mm_processor_cache_gb,
                 mm_processor_cache_type=mm_processor_cache_type,
                 mm_shm_cache_max_object_size_mb=mm_shm_cache_max_object_size_mb,
+                mm_encoder_only=mm_encoder_only,
                 mm_encoder_tp_mode=mm_encoder_tp_mode,
                 mm_encoder_attn_backend=mm_encoder_attn_backend,
                 interleave_mm_strings=interleave_mm_strings,