Add config_format and load_format to vLLM args

README.md

@@ -338,7 +338,7 @@ We recommend to 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=10' --tensor-parallel-size 8
+vllm serve mistralai/Pixtral-Large-Instruct-2411 --config-format mistral --load-format mistral --tokenizer_mode mistral --limit_mm_per_prompt 'image=10' --tensor-parallel-size 8
 ```
 
 2. And ping the client:
@@ -523,7 +523,7 @@ messages = [
 sampling_params = SamplingParams(max_tokens=512)
 
 # note that running this model on GPU requires over 300 GB of GPU RAM
-llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8, limit_mm_per_prompt={"image": 4})
+llm = LLM(model=model_name, config_format="mistral", load_format="mistral", tokenizer_mode="mistral", tensor_parallel_size=8, limit_mm_per_prompt={"image": 4})
 
 outputs = llm.chat(messages, sampling_params=sampling_params)