debug

app.py

@@ -32,7 +32,7 @@ LLM_MODEL_PATH = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
 processor = AutoProcessor.from_pretrained(MLLM_MODEL_PATH)
 tokenizer = AutoTokenizer.from_pretrained(LLM_MODEL_PATH)
 
-mllm = LLM(model=MLLM_MODEL_PATH, tensor_parallel_size=1, gpu_memory_utilization=0.8,
+mllm = LLM(model=MLLM_MODEL_PATH, gpu_memory_utilization=0.8,
            device='cuda:0', dtype="bfloat16", limit_mm_per_prompt={"image": 1})
 
 llm = LLM(model=LLM_MODEL_PATH, tensor_parallel_size=1, gpu_memory_utilization=0.8,