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

Recommend AWS EC2 Instance ? #194

Closed
hamzanaeem1999 opened this issue Dec 16, 2022 · 2 comments
Closed

Recommend AWS EC2 Instance ? #194

hamzanaeem1999 opened this issue Dec 16, 2022 · 2 comments

Comments

@hamzanaeem1999
Copy link

hamzanaeem1999 commented Dec 16, 2022

I want to use in-depth functionality of lama and I want to use the refine=True parameter and i come to know that it consumes 24GB VRAM. Can some one recommend any ec2 instance with handsome gpu and good memory . That ec2 instance GPU should be cuda enabled . I have seen G Series but it is so confusing ? My ultimate goal is to just do the predictions with refine=True to see the results.
@windj007
@cohimame
@Sanster

@windj007
Copy link
Collaborator

I'd recommend first allocating a big instance with a lot of VRAM, try what you want and see how much it consumes - and then find the minimal instance that fits.

@iamdanniemirz
Copy link

@hamzanaeem1999 AOA Hamza, Have you tested the Lama on EC2 ... Please tell me how much resources are required to run Lama with refinement and which EC2 GPU instance you chose?

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

No branches or pull requests

3 participants