R
RunPod•5mo ago
Builderman

streaming

i'm used to using openai to stream text all in one request that is done async. why does runpod just spam requests for the /stream endpoint instead of making it one request and feeding data as it's generated?
3 Replies
andrew
andrew•5mo ago
deadass why yall doing that fr
Builderman
Builderman•5mo ago
theres gotta be a way
andrew
andrew•5mo ago
i spent an hour setting up streaming thinking yall were actually streaming the data live 😭
Want results from more Discord servers?
Add your server
More Posts
open portsI would like to open the posts in my instance, how do I do it?[Urgent] One GPU suddenly went awayHi, we have prod issue right now one of the gpu from our pod suddently disapparedIssue with Worker Initiation Error Leading to Persistent "IN_PROGRESS" Job StatusHi All, While testing the endpoint, I observed that when initiating a job with an empty input in thDoes GPU Cloud service support Illyasviel/Fooocus AI?My pc has low vram and always get disconnections from the fooocus ai, im interested to upgrade with Log retention and privacyI'm weighing the cost benefit of cloud GPU for AI inference tasks and self-hosted vs privacy implicaPod suddenly says "0x A100 80GB" and cuda not availableHi, I created a pod a few days ago and worked with it, no problem. I stopped the pod after the sessiServerless doesn't work properly when docker image is committedI built the image locally using the following command and it works fine after submitting it to serveMoving storage locationMy storage drive is in region EU-CZ-1. But there are no pods available to launch. Is there anyway I [Errno 122] Disk quota exceededMy workers are occasionally getting this error, which I've never seen before: { "dt": "2024-01-12Error whilst using Official A1111 Runpod Worker - CUDA error: an illegal instruction was encounteredhttps://github.com/runpod-workers/worker-a1111 I am using the official A1111 Runpod Worker. It's no