Update README.md

README.md

@@ -248,13 +248,10 @@ print(outputs[0].outputs[0].text)
 
 ### **Use it with vLLM**
 
-The snippet below shows how to use this model with vLLM. Use the following [commit](https://github.com/vllm-project/vllm/commit/75531a6c134282f940c86461b3c40996b4136793) and follow these instructions to build and install vLLM in a docker container.
+The snippet below shows how to use this model with vLLM. Use the latest version of vLLM and follow these instructions to build and install vLLM.
 
 ```shell
-git clone https://github.com/vllm-project/vllm.git
-cd vllm
-git checkout bf756321c72340466911b64602e88013d0210c1c
-VLLM_USE_PRECOMPILED=1 pip install -e .
+pip install -U "vllm>=0.10.1"
 ```
 
 Now you can run run the server with:
@@ -265,6 +262,7 @@ vllm serve nvidia/NVIDIA-Nemotron-Nano-9B-v2 \
     --mamba_ssm_cache_dtype float32
 ```
 
+
 Note: Remember to add \`--mamba\_ssm\_cache\_dtype float32\` for accurate quality. Without this option, the model’s accuracy may degrade.
 
 #### Using Budget Control with a vLLM Server