Add Model Revision Support (#1014)

Co-authored-by: Jasmond Loh <Jasmond.Loh@hotmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

vllm/model_executor/models/qwen.py

@@ -251,13 +251,14 @@ class QWenLMHeadModel(nn.Module):
         model_name_or_path: str,
         cache_dir: Optional[str] = None,
         load_format: str = "auto",
+        revision: Optional[str] = None,
     ):
         tp_world_size = get_tensor_model_parallel_world_size()
         tp_rank = get_tensor_model_parallel_rank()
         state_dict = self.state_dict()
 
         for name, loaded_weight in hf_model_weights_iterator(
-                model_name_or_path, cache_dir, load_format):
+                model_name_or_path, cache_dir, load_format, revision):
             if "rotary_emb.inv_freq" in name:
                 continue