R
RunPod•4mo ago
Magistrum

Out of memory errors on 48gb gpu which didn't happen before

Some requests fail due to OOM, but the endpoint uses 48gb and is definitely capable of processing these requests
0 Replies
No replies yetBe the first to reply to this messageJoin
Want results from more Discord servers?
Add your server
More Posts
H100 multi-gpus settingsWhen I tried to load weights from checkpoints on my custom model using multi-gpus, weights are not lContainer fails to start randomlyContainer fails to start randomly error pod id **840b98harmlsgb wqaz2xufma32pt eqyabu82t6l3y9** sysIs it possible to run fully on sync?All the async functions and webhooks are so much pain, can we just fully run on sync?How to keep worker memory after completing request?Hi! I'm running serverless for model GAN. I want preload model in memory at the first request and re