Update demo/infer.py

demo/infer.py

@@ -36,9 +36,8 @@ class LiveCCDemoInfer:
         self.model = Qwen2VLForConditionalGeneration.from_pretrained(
             model_path, torch_dtype="auto", 
             device_map=device, 
-            # attn_implementation='flash_attention_2'
+            attn_implementation='sdpa'
         )
-        self.model.to(device)
         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)