Billing increases last two days heavily from delay time in RTX 4000 Ada
I checked my billing history and I saw that my serverless bills increased a lot and the culprit is the usage of RTX 4000 Ada.
I checked the log and it's because of CUDA runtime error as ONNX runtime doesn't work with this specific GPU. This causes the container to retry again and again, increasing the delay time.
I have never met this issue before so I'm not sure why it's happening now without any code change on my side.
Can runpod give me coupon to redeem last 2 days of error?
Also how do I prevent the usage of RTX 4000 Ada from now on?
5 Replies
u can ping @flash-singh with ur details of account id / endpoint so they can verify the logs / fix it up + give u ur credit back
you can edit endpoint and uncheck the 4000 ada, also set max execution time to be safe
for any refunds you can reach out to support from web chat, but considering what happened here, it would be an uphill battle, we usually give refunds depending on if its an issue on our end or yours, something you can control
I'm not sure whether Runpod has updated anything on the 4000 Ada machine because this kind of cost has never happened to me before and I always tick 4000 Ada.
Also @flash-singh why is the web support give me access to a chatbot rather than a real human?
I can't even switch to a real human and this chatbot is basically useless when anyone needs a real support. I only see the real human support available in mobile
always starts with AI bot
say 'speak to a live agent' and nothing else
most chatbots (support ones) wait till you say that, otherwise its gonna not gonna care