⚠ Hundreds of unexplained requests coming in
🔴 We have started to experience a sudden influx of requests on all of our production endpoints, first started a month ago, but now its getting more frequent, like every day in the past 2-3 days, around this time. (when i posted this)
These requests are not coming from us, since the jobs that we actually submitted and are in the queue are below a 100 at this timeframe.
I've already rotated the API keys, but its still happening.
Any way to figure this out?...
Using Multi process pool with serverless cpu sometime cannot stop.
for My Script speed increase. I use multiprocess for my LLM Translation (open-AI API Usage (LangChain)). but Sometime the worker stop with 0% cpu usage in very long time.
Runpod Servelerss really unreliable, delay time is way too high sometimes
I'm using a 24 GB vRAM serverless endpoint, the endpoint is way too unstable, 90% of the times the "QUEUE" takes a couple of seconds and then inference of the Omniparser v2 model takes between 3-8 seconds.
This is a replicable result in Google Colab and other GPUs, nonetheless, every once on a while Runpod takes more than 40 seconds ofr even minutes to process a request. This happens when a specific worker bugs and then multiple request goes through it. The worker bugs for no reason and takes multiple minutes to do the job it should do in seconds. This only happens for some workers and when the same worker is used multiple times, it makes no sense and Runpod charges you multiple minutes of DELAY TIME, sometimes it does not even go through, meaning it says "IN_PROGRESS" as seen in the image for multiple minutes without finishing while Runpod charges you every second.
In any other environment and even runpod this process takes seconds, the "IN_PROGRESS" print shows between 3-8 times only. This makes the endpoint highly unstable and way too expensive for a model that does not even use half of the vRAM....
