Update README.md

README.md

@@ -82,10 +82,10 @@ if __name__ == '__main__':
 #### Online Inference
 ```shell
 vllm serve inclusionAI/Ring-mini-linear-2.0-GPTQ-int4 \
-              --tensor-parallel-size 2 \
+              --tensor-parallel-size 1 \
               --pipeline-parallel-size 1 \
               --gpu-memory-utilization 0.90 \
-              --max-num-seqs 512 \
+              --max-num-seqs 128 \
               --no-enable-prefix-caching
 ```