Skip to content

Conversation

@sindhuvahinis
Copy link
Contributor

Description

  • prepare.py has serving.properties, which has option.model_id=gpt2
  • and env has HF_MODEL_ID also has gpt2. So it is loading the model again, which leads to OOM.

https://github.com/deepjavalibrary/djl-serving/actions/runs/9698967044/job/26767133000#step:7:476

@sindhuvahinis sindhuvahinis requested review from a team, frankfliu and zachgk as code owners June 28, 2024 21:31
@sindhuvahinis sindhuvahinis merged commit 4fc9eb5 into deepjavalibrary:master Jun 28, 2024
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.

3 participants