Update README.md

README.md

@@ -55,7 +55,7 @@ Install **vLLM** and
     run the [server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#openai-compatible-server):
     
 ```
-python -m vllm.entrypoints.openai.api_server --model cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic
+python -m vllm.entrypoints.openai.api_server --model cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic --max-model-len 9000 --gpu-memory-utilization 0.95
 ```
 Access the model:
 ```