[V1][Spec Decoding] Use model_loader.get_model() to load models (#18273)

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-05-23 03:05:44 +01:00
parent 04eb88dc80
commit c6b636f9fb
16 changed files with 59 additions and 135 deletions
--- a/vllm/model_executor/model_loader/utils.py
+++ b/vllm/model_executor/model_loader/utils.py
@@ -42,9 +42,11 @@ def initialize_model(
    *,
    prefix: str = "",
    model_class: Optional[type[nn.Module]] = None,
+    model_config: Optional[ModelConfig] = None,
 ) -> nn.Module:
    """Initialize a model with the given configurations."""
-    model_config = vllm_config.model_config
+    if model_config is None:
+        model_config = vllm_config.model_config
    if model_class is None:
        model_class, _ = get_model_architecture(model_config)