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

support eager attention #30

Merged

aria-hacker merged 1 commit into main from eager_attn

Oct 15, 2024

Collaborator

aria-hacker commented Oct 15, 2024 •

edited

Loading

ref #29

We can now enable eager attention by setting attn_implementation='eager' in the from_pretrained method when loading the model

model = AutoModelForCausalLM.from_pretrained(
    model_id_or_path,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    attn_implementation="eager",
)


          support eager attention

aria-hacker merged commit a0b0690 into main

1 check passed

aria-hacker deleted the eager_attn branch

October 15, 2024 12:01

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet