fix

demo/infer.py

@@ -34,9 +34,10 @@ class LiveCCDemoInfer:
     def __init__(self, model_path: str = None, device_id: int = 0):
         self.model = Qwen2VLForConditionalGeneration.from_pretrained(
             model_path, torch_dtype="auto", 
-            device_map=f'cuda:{device_id}', 
-            attn_implementation='flash_attention_2'
+            # device_map=f'cuda:{device_id}', 
+            # attn_implementation='flash_attention_2'
         )
+        self.model.to('cuda')
         self.processor = AutoProcessor.from_pretrained(model_path, use_fast=False)
         self.streaming_eos_token_id = self.processor.tokenizer(' ...').input_ids[-1]
         self.model.prepare_inputs_for_generation = functools.partial(prepare_multiturn_multimodal_inputs_for_generation, self.model)