[Request] Runpod Serverless Version of the Llama4-Scout Deployment Recipe

[celsofranssa]

I was going through the excellent Llama 4 Scout on vLLM recipe

Would it be possible to provide a version of this recipe adapted for Runpod vLLM Serverless
In particular, guidance on the required GPUs and the appropriate vLLM configuration would be very helpful.

This would make it much easier for those of us looking to deploy on Runpod’s serverless platform directly.

Thanks a lot for considering this! 🙏

[celsofranssa]

vllm-project/recipes#37