Closed DeepAlgoExpert closed 4 months ago
killed means not enough RAM usually
killed means not enough RAM usually @yisol can u reveal the specifications it requires to launch ,details about cpu n gpu etc @FurkanGozukara please can u estimate how much it requires , because I'm using 16GB Memory and 24GB gpu still same error @DeepAlgoExpert did u solve ??
well we have even 8 GB VRAM working version
even if you dont have sufficient RAM it should work with virtual RAM
for Windows : https://youtu.be/m4pcIeAVQD0 for linux / ubuntu : https://youtu.be/LeHfgq_lAXU
I get same error while tring to run command
python gradio_demo/app.py
But i have 16 GB RAM and every time when i run this command it acquirer all 16 GB ram and it caused my pc was hanged. So please provide solution for that.
I get same error while tring to run command
python gradio_demo/app.py
But i have 16 GB RAM and every time when i run this command it acquirer all 16 GB ram and it caused my pc was hanged. So please provide solution for that.
the same. Have u solved the problem?
I have 64g of RAM and 24g of GPU memory, but the same error message appears. It's puzzling.
@longding717 yeah while doing setup it eataways time but it actually works , I used g5.2xlarge 8vCPUs 32 gb Memory EC2 Instance ,works for me . In local also we can run I was able to launch in NVIDIA GeForce RTX 3070 Mobile / Max-Q Memory: 32.0 GiB GDDR6
Getting the same issue.
Laptop config= 8 cores CPU, 1660 4gb RAM GeforceGTX GPU, 16 GB RAM and 512GB SSD.
Any possible fix to the issue please help me out.
@Utkarsh13tiwari can u share error ?
@SailochanaR
error:
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file. Killed
there is no error, but seems to some problem with memory according to the previous comments/suggestions. Look the above warning
@Utkarsh13tiwari
The issue is with insufficient memory, u require 32GB memory, even I faced same Error .
Ur Error : concludes with launching
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
At this point the model configures the system requirements after this it will load UNET model files
@SailochanaR So whats the possible fix? should i use AWS ec2 instance for running the API?
How did you overcome the error?
@Utkarsh13tiwari yes . I used g5.2xlarge 8vCPUs 32 gb Memory EC2 Instance
Thanks for your great work. I tried to run gradio demo on ubuntu with cuda 11.8 but got error. Please help me! Thanks.