Update README.md

[DOC] update vllm startup command

README.md

@@ -58,6 +58,11 @@ see [Official vLLM Deepseek-V3.2 Guide](https://docs.vllm.ai/projects/recipes/en
 
 ```
 export VLLM_USE_DEEP_GEMM=0  # ATM, this line is a "must" for Hopper devices
+export TORCH_ALLOW_TF32_CUBLAS_OVERRIDE=1
+export VLLM_USE_FLASHINFER_MOE_FP16=1
+export VLLM_USE_FLASHINFER_SAMPLER=0
+export OMP_NUM_THREADS=4
+
 CONTEXT_LENGTH=32768
 vllm serve \
     __YOUR_PATH__/QuantTrio/DeepSeek-V3.2-AWQ \