Update README.md

README.md

@@ -234,7 +234,7 @@ messages = [
 sampling_params = SamplingParams(max_tokens=128_000)
 
 # note that running this model on GPU requires over 300 GB of GPU RAM
-llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel=8, limit_mm_per_prompt={"image": 4})
+llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8, limit_mm_per_prompt={"image": 4})
 
 outputs = llm.chat(messages, sampling_params=sampling_params)
 
@@ -249,7 +249,7 @@ You can also use Pixtral-Large-Instruct-2411 in a server/client setting.
 1. Spin up a server:
 
 ```
-vllm serve mistralai/Pixtral-Large-Instruct-2411 --tokenizer_mode mistral --limit_mm_per_prompt 'image=4'
+vllm serve mistralai/Pixtral-Large-Instruct-2411 --tokenizer_mode mistral --limit_mm_per_prompt 'image=4' --tensor_parallel_size 8
 ```
 
 2. And ping the client: