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

Add mark_step for encoder layers #650

Open
wants to merge 2 commits into
base: habana_main
Choose a base branch
from

Conversation

yisonzhu
Copy link

@yisonzhu yisonzhu commented Dec 19, 2024

Coupled with [Use FusedSDPA for MllamaVisionSdpaAttention #620], these two issues arising when running llama3.2 vision model can be resolved:

  1. GC fail when batchsize>1 on Gaudi3.
  2. Increased device memory consumption with Torch 2.5 compared to Torch 2.4.

Copy link

@jkaniecki jkaniecki left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@yisonzhu yisonzhu requested a review from vivekgoe as a code owner December 25, 2024 04:42
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

Successfully merging this pull request may close these issues.

2 participants