R
RunPod•4mo ago
MrFox

Similar speed of workers on different GPUs

Hi, I am trying to launch the codeformer model on a serverless GPU. However, during testing I've noticed that it doesn't matter which GPU I choose, the speed would stay the same. So a100 works with the almost identical speed as with a4500. How could I fix that issue?
Solution:
Main benefit of A100 is VRAM not performance, if you want performance, select 24GB PRO which is 4090.
Jump to solution
2 Replies
Solution
ashleyk
ashleyk•4mo ago
Main benefit of A100 is VRAM not performance, if you want performance, select 24GB PRO which is 4090.
MrFox
MrFox•4mo ago
Thank you. Looks like the issue was only from my side.
Want results from more Discord servers?
Add your server
More Posts
Docker daemon is not started by default?In the template I specify docker run command, but the worker cannot execute the container because daVLLM Worker Error that doesn't time out.``` 2024-02-01T18:08:19.928745487Z {"requestId": null, "message": "Traceback: Traceback (most recentProxy Url related infoi am having error CNAME Cross-User Banned when try to register runpod proxy url in cloudflare cnameDeploying a PDF converter app to serverlessHey I'm new to runpod, I'd like to run an app that utilizes some OCR models to convert pdf files to Managing savings plan using graphql APIHi Runpod teams! I'm currently using multiple GPU pods in secure cloud and planning to utilize savinquick python vLLM endpoint example please?…I’ve been on this for 2 hours and the best I can get so far is have a bunch of stuff endlessly ‘que"There are no longer any instances available with enough disk space" from graphqlThis is the mutation I'm sending: mutation { podFindAndDeployOnDemand( input: { Best way to deploy a new LLM serverless, where I don't want to build large docker imagesThe infrastructure I have come across at runpod, there is not much support for serverless for fast cPause on the yield in async handlerI have wrote async handler. Messages are realy small, about several kilobites async for msg in searworker-vllm cannot download private modelI built my model successfully and it was able to download it during the build. However, when I deplo