Update vllm/model_executor/model_loader/utils.py

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Signed-off-by: Nandan Vallamdasu  <[email protected]>
Signed-off-by: nandan2003 <[email protected]>

Author: nandan2003

vllm/model_executor/model_loader/utils.py

@@ -166,7 +166,7 @@ def device_loading_context(module: torch.nn.Module, target_device: torch.device)
 """Caches the outputs of `_get_model_architecture`."""
 
 
-def _get_model_architecture(model_config: ModelConfig) -> tuple[type[nn.Module], str, bool]:
+def _get_model_architecture(model_config: ModelConfig) -> tuple[type[nn.Module], str]:
     from vllm.model_executor.models.adapters import (
         as_embedding_model,
         as_reward_model,