R
RunPod•4mo ago
fanbing

When using runpodctl project dev to upload a project, is there a speed limit?

From my tests, the speed seems to be around 1.2MB per second. When uploading for the first time, the various large models combined exceed 10GB, which takes a considerable amount of time to complete.
7 Replies
ashleyk
ashleyk•4mo ago
No speed limit, depends on your internet connection to the destination.
Madiator2011
Madiator2011•4mo ago
Two better ways either use croc or my uploader tool 😄
fanbing
fanbing•4mo ago
Your uploader tool is ?
Madiator2011
Madiator2011•4mo ago
https://github.com/kodxana/RunPod-FilleUploader
GitHub
GitHub - kodxana/RunPod-FilleUploader: Web UI for easy file upload ...
Web UI for easy file upload to runpod pods. Contribute to kodxana/RunPod-FilleUploader development by creating an account on GitHub.
fanbing
fanbing•4mo ago
I will to look, thank you
Madiator2011
Madiator2011•4mo ago
though if you would like to use it you would need to either install it on pod and expose port 2999 or use template that have it preincluded ashleyk added my tool to his templates
nathaniel
nathaniel•4mo ago
@Papa Madiator sounds like this was done through file sync on cli, should we default to using croc or something specialized for large files such as this? Right now it always uses rsync
Want results from more Discord servers?
Add your server
More Posts
Request Stuck in QueueHavent seen a single log, dont know where to start debuggingNetwork issues with 3090 podsPods `tfc6texf3xrkip` and `33laj8z8yzm0du` both have borked networking. The download speeds are veryWhy serverless endpoint download sdxl1.0 from hugging Face hub so slow?My project need download sdxl 1.0 form hugging face hub, about 7G,but after waiting 50minutes, job iI am getting no response from serverlesswhile i am testing my image, i am getting no response, no errors, CPU usage is 100%. Is it because isecure connectionsI want to ensure all traffic between my app and the server less backend is encrypted. Does the endposerver less capability checkI want to add runpod into a tier of load balanced llm models behind an app like openrouter.ai, but tGPU memory usage is at 99% when starting the task.I started to notice some GPU OOM failure today, and it's specific to this instance: A40 - 44adfw5inhShould i wait for the worker to pull my imageI have a large image (100 GB), should i wait for worker to pull the image before starting any inferePossible memory leak on ServerlessWe're testing different mistral models (cognitivecomputations/dolphin-2.6-mistral-7b and TheBloke/doare we able to run DinD image for GPU pods?Hi, anyone tried running DinD in GPU pods?