Job Stuck in Queue Eventhough worker is ready
I am using serverless endpoint with H100 but I am experiencing high queue time .If you send a single request to runpod enpoint you may get 2 seconds delay time and on same 2nd request you will get queue time of 7 seconds which should not happend.I think they should optimize their queue and worker communication codes
ist run: 3 seconds
2nd run: 15.84 seconds
8 Replies
Same here!
Same here
Big issue!
Workers are "running" but they're not working on any requests, and requests just sit there for 10m+ queued up without anything happening
@Justin Merrell @flash-singh
@Felipe Fontana, @Saqib Zia Can you share an endpoint ID? We're looking into this.
@Dj This one 753fhxwxx4a7j8
Thank you! We're looking into this.
Same issue!
@Dj I have this endpoint id : 67eg8a5ud7cl67
I have even created network volume to test it still the results are same we cannot move into production with this variablity in response time
Thank you, on-call engineering is working on this issue - I'll keep you updated over the coming hours.