Update Qwen1.5-7b_single_dcu_inference.py

inference/inference_vllm/Qwen1.5-7b_single_dcu_inference.py

-
 from vllm import LLM, SamplingParams
 # Sample prompts.
 prompts = [
     "The capital of France is",
 ]
 # Create a sampling params object.
-sampling_params = SamplingParams(temperature=0.8, top_p=0.95,top_k=50,stop="</s>")
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 
 # Create an LLM.
 llm = LLM(model="./qwen2/Qwen1.5-7B-Chat",trust_remote_code=True,dtype="float16", enforce_eager=True)
@@ -16,4 +15,4 @@ outputs = llm.generate(prompts, sampling_params)
 for output in outputs:
     prompt = output.prompt
     generated_text = output.outputs[0].text
-    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
\ No newline at end of file
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")