Dear NVIDIA Team,
I am actively developing a multi-step LLM workflow utilizing the NIM API, which involves sequential model invocations. The current 40 RPM rate limit is significantly constraining my development progress and has become a critical bottleneck.
Frequent 429 errors due to the rate limitation are severely impacting my ability to efficiently debug and validate core logic. As the complexity of my workflows requires continuous, uninterrupted processing, the existing quota is insufficient to support even basic testing cycles. Elevating the account-level rate limit to 200 RPM would effectively address this constraint and ensure smooth execution of end-to-end workflows.
Kindly assist in adjusting the rate limit for my account (Registered Email: TheronY347@gmail.com) to facilitate timely testing and advancement of the project.
I am prepared to provide additional details on my use case if required. Your support is greatly appreciated.
Best regards,
TheronY