Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Installation error on NVIDIA GeForce RTX 4090 #61

Open
bilalaliofficial opened this issue Aug 9, 2024 · 7 comments
Open

Installation error on NVIDIA GeForce RTX 4090 #61

bilalaliofficial opened this issue Aug 9, 2024 · 7 comments

Comments

@bilalaliofficial
Copy link

I’m trying to install this package on an RTX 4090 GPU, but it is giving me the following error:

./build-whisper.sh: line 17: 12 Aborted (core dumped) python3 build.py --output_dir whisper_small_en --use_gpt_attention_plugin --use_gemm_plugin --use_bert_attention_plugin --enable_context_fmha --model_name small.en whisperfusion-1 exited with code 134
image

Nvidia SMI

image

Please help me to resolve this issue

@makaveli10
Copy link
Collaborator

Isn't the gpu is fully utilised already, can you try again after clearing some space on the GPU?

@bilalaliofficial
Copy link
Author

Yes, I got it and solved this issue and it's showing no error and running but when I'm trying to load on browser not working

image
image

image

@makaveli10
Copy link
Collaborator

Its should be available on localhost:8000

@bilalaliofficial
Copy link
Author

Yes, I got it but this GPU is deployed on the network, and I'm accessing it from my laptop.

@makaveli10
Copy link
Collaborator

makaveli10 commented Aug 21, 2024

In that case can you try forwarding the ports(8000, 8888, 6006) from the network to your local and then try accessing localhost:8000

@goranskular
Copy link

How did you resolve the core dump issue? Thanks

@ananpalliyal
Copy link

@bilalaliofficial hello did you get it running? I'm also trying to run whisperfusion on a rtx 4090 cloud instance the problem is that this gpu instance doesn't support docker, so I have to do everything manually.
also, where did you get your rtx 4090 from?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

4 participants