Update README.md

README.md

@@ -14,7 +14,7 @@ docker network create vllm
 docker run --runtime=nvidia --gpus all --network vllm --name vllm -v vllm_cache:/root/.cache/huggingface --env "HUGGING_FACE_HUB_TOKEN=..." --env "HF_HUB_ENABLE_HF_TRANSFER=0" -p 8000:8000 --ipc=host vllm/vllm-openai:latest --model Yujivus/Phi-4-Health-CoT-1.1-AWQ --quantization awq_marlin --dtype float16 --gpu_memory-utilization 0.95 --max-model-len 2500
 
 You can test vLLM's speed :
-""""
+
 import asyncio
 from openai import AsyncOpenAI
 
@@ -73,7 +73,7 @@ async def main():
 
 if __name__ == "__main__":
     asyncio.run(main())
-""""
+
 
 Since the model is quantized awq-gemm, you should see max throughtput for 8 requests.