Request to Increase Serverless Workers Quota
I am writing to request an increase in my serverless workers quota for my account (pengtrym@gmail.com).
My current quota is 5 max workers across all endpoints.
My goal is to deploy several large AI models (such as SDXL, SD3, and FLUX) on your serverless platform. To ensure fast cold starts and proper scalability, I plan to follow the best practice of deploying each model as its own dedicated serverless endpoint.
With the current quota of 5, I am unable to implement this architecture. Deploying 4-5 different models would limit me to only 1 max worker per endpoint, which is insufficient for development and production use.
To support this multi-model deployment and allow for reasonable auto-scaling, could you please increase my total serverless workers quota to 30 (or a more appropriate number you see fit)?
Thank you for your assistance.
Best regards,
Peng
My current quota is 5 max workers across all endpoints.
My goal is to deploy several large AI models (such as SDXL, SD3, and FLUX) on your serverless platform. To ensure fast cold starts and proper scalability, I plan to follow the best practice of deploying each model as its own dedicated serverless endpoint.
With the current quota of 5, I am unable to implement this architecture. Deploying 4-5 different models would limit me to only 1 max worker per endpoint, which is insufficient for development and production use.
To support this multi-model deployment and allow for reasonable auto-scaling, could you please increase my total serverless workers quota to 30 (or a more appropriate number you see fit)?
Thank you for your assistance.
Best regards,
Peng
