R
RunPod•3mo ago
slack

Slowish Downloads

I'm trying to setup a pod running ComfyUI for Flux at the moment, and it's going to take 30-40 mins just to download the models with the speed it's running at.
Downloading 1 model(s) to /workspace//storage/stable_diffusion/models/unet...
Downloading: https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/flux1-dev.safetensors

0K .......... .......... .......... .......... .......... 0% 10.9M 34m23s
204800K .......... .......... .......... .......... .......... 1% 10.3M 35m7s
409600K .......... .......... .......... .......... .......... 2% 10.4M 34m59s
614400K .......... .......... .......... .......... .......... 3% 10.5M 34m40s
819200K .......... .......... .......... .......... .......... 4% 13.7M 32m47s
1024000K .......... .......... .......... .......... .......... 5% 11.9M 32m4s
1228800K .......... .......... .......... .......... .......... 6% 11.6M 31m36s
1433600K .......... .......... .......... .......... .......... 7% 22.0M 29m23s
1638400K .......... .......... .......... .......... .......... 7% 20.4M 27m46s
1843200K .......... .......... .......... .......... .......... 8% 12.3M 27m34s
2048000K .......... .......... .......... .......... .......... 9% 11.2M 27m35s
2252800K .......... .......... .......... .......... .......... 10% 12.5M 27m18s
2457600K .......... .......... .......... .......... .......... 11% 12.6M 27m0s
2662400K .......... .......... .......... .......... .......... 12% 18.6M 26m6s
2867200K .......... .......... .......... .......... .......... 13% 13.6M 25m44s
3072000K .......... .......... .......... .......... .......... 14% 10.8M 25m46s
Downloading 1 model(s) to /workspace//storage/stable_diffusion/models/unet...
Downloading: https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/flux1-dev.safetensors

0K .......... .......... .......... .......... .......... 0% 10.9M 34m23s
204800K .......... .......... .......... .......... .......... 1% 10.3M 35m7s
409600K .......... .......... .......... .......... .......... 2% 10.4M 34m59s
614400K .......... .......... .......... .......... .......... 3% 10.5M 34m40s
819200K .......... .......... .......... .......... .......... 4% 13.7M 32m47s
1024000K .......... .......... .......... .......... .......... 5% 11.9M 32m4s
1228800K .......... .......... .......... .......... .......... 6% 11.6M 31m36s
1433600K .......... .......... .......... .......... .......... 7% 22.0M 29m23s
1638400K .......... .......... .......... .......... .......... 7% 20.4M 27m46s
1843200K .......... .......... .......... .......... .......... 8% 12.3M 27m34s
2048000K .......... .......... .......... .......... .......... 9% 11.2M 27m35s
2252800K .......... .......... .......... .......... .......... 10% 12.5M 27m18s
2457600K .......... .......... .......... .......... .......... 11% 12.6M 27m0s
2662400K .......... .......... .......... .......... .......... 12% 18.6M 26m6s
2867200K .......... .......... .......... .......... .......... 13% 13.6M 25m44s
3072000K .......... .......... .......... .......... .......... 14% 10.8M 25m46s
Download speed has been much faster in the past. Pod ID: v4kbmqzmcyr3yf
32 Replies
utmostmick0
utmostmick0•3mo ago
yeah should b 3-4x that speed , what command did u use to download ?
slack
slackOP•3mo ago
the script is just using wget it was running this provisioning script: https://raw.githubusercontent.com/ai-dock/comfyui/main/config/provisioning/flux.sh
utmostmick0
utmostmick0•3mo ago
wget --header="Authorization: Bearer <HF_Token>" url ^^ command i use replace <HF_Token> with your hf token no brackets
Peter Peter
Peter Peter•3mo ago
Experiencing the same issue again, we transferred from EU-is-1 because it was terribly slow, but now the RO Secure cloud is slow as well. These slowdows are started like a month ago, and we cannot continue using Runpod if this issue persist any longer. We are losing prestige because of this. 2024-09-03T10:02:48Z 79d44721116c Downloading [===========> ] 987.1MB/4.481GB 2024-09-03T10:02:48Z 79d44721116c Downloading [===========> ] 987.6MB/4.481GB 2024-09-03T10:02:48Z 79d44721116c Downloading [===========> ] 988.2MB/4.481GB 2024-09-03T10:02:49Z 79d44721116c Downloading [===========> ] 988.7MB/4.481GB 2024-09-03T10:02:49Z 79d44721116c Downloading [===========> ] 989.3MB/4.481GB 2024-09-03T10:02:49Z 79d44721116c Downloading [===========> ] 989.8MB/4.481GB
slack
slackOP•3mo ago
Yeah I gave up waiting earlier, not keen on paying for an hour of waiting on downloads. Hopefully something can be fixed
Peter Peter
Peter Peter•3mo ago
Yep, we are getting calls from paying customers nonstop
utmostmick0
utmostmick0•3mo ago
with that command i download flux1.dev in about 9mins
Peter Peter
Peter Peter•3mo ago
Okay you are probably using another datacenter or another machine in the datacenter.
utmostmick0
utmostmick0•3mo ago
EU-SE-1 normally on a A40
Peter Peter
Peter Peter•3mo ago
Okay we are experiencing the slowdown in the RO datacenter
utmostmick0
utmostmick0•3mo ago
if you download it with the command i posted how fast is it ?
Peter Peter
Peter Peter•3mo ago
We are not even there, currently the image is still pulling
utmostmick0
utmostmick0•3mo ago
what image ?
Peter Peter
Peter Peter•3mo ago
Docker image
utmostmick0
utmostmick0•3mo ago
the pod ? which template ?
Peter Peter
Peter Peter•3mo ago
Custom
utmostmick0
utmostmick0•3mo ago
ahhh idk then dude , mayb put in a support ticket takes me about 30-40 tops to restart from scratch when i trash a pod where are you pulling your docker container from ? fuck that server is painfully slow
Peter Peter
Peter Peter•3mo ago
The image was publicly hosted on github, but it was insanely slow so I rehosted it on docker hub, it helped somewhat.
utmostmick0
utmostmick0•3mo ago
yeah i was going to say put it on docker hub , I just spun up a pod and downloaded the template i normally use and its slow af might be an idea to change servers
inc3pt.io
inc3pt.io•3mo ago
Also slow for serverless image downloading from Docker Hub. On a CPU machine (cpu3c-32-64)
Myron
Myron•3mo ago
I'm experiencing the same issue downloading from dockerhub on EU-RO-1 We can't use runpod with this type of performance, we need to be able to scale up and down faster than this. If this doesn't get resolved we'll be forced to look for an alternative.
Poddy
Poddy•3mo ago
@slack
Escalated To Zendesk
The thread has been escalated to Zendesk!
Myron
Myron•3mo ago
👌
No description
nerdylive
nerdylive•3mo ago
Create another one 🙂
Myron
Myron•3mo ago
Madiator2011 (Work)
Madiator2011 (Work)•3mo ago
EU-RO-1 region had recently network being worked one that should now make connections faster. EU-RO-1 is huge demand region so it's higher network usage.
Myron
Myron•3mo ago
Being able to tell demand per region would be great so we can make a more educated choice when it comes to which region to pick.
Encyrption
Encyrption•3mo ago
Should be able to gleam that info from GraphQL, which provides data about availability.
Myron
Myron•3mo ago
Where in spec can I find it? It's a bit hard to navigate haha
Encyrption
Encyrption•3mo ago
Myron
Myron•3mo ago
That wouldn't show overal demand right? Just how many GPUs are used etc?
Encyrption
Encyrption•3mo ago
Yeah, was thinking could do that query per region but not seeing that option. 😦
Want results from more Discord servers?
Add your server