Skip to content

A single A100-80G can't run Llama-2-70b model? #106

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.

Sign up for GitHub

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

Jump to bottom
Open
JustVelkhana opened this issue Apr 17, 2025 · 1 comment
Open

A single A100-80G can't run Llama-2-70b model? #106

JustVelkhana opened this issue Apr 17, 2025 · 1 comment

Comments

@JustVelkhana
Copy link

We meet out of memory. Adding '--multigpu' doesn't work though.
@JustVelkhana
Copy link
Author

our setting
CUDA_VISIBLE_DEVICES=2,3 python main.py
--model /cache/model/Llama-2-70b-hf
--epochs 20 --output_dir ./log/Llama-2-70b-w4a16
--wbits 4 --abits 16 --lwc
--tasks piqa
--act-scales /cache/pt_for_let/Llama-2-70b-hf_scales.pt --act-shifts /cache/pt_for_let/Llama-2-70b-hf_shifts.pt
--multigpu

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@JustVelkhana