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 static shape support for vision_encoder_decoder generation if dec… #834

Merged
merged 2 commits into from
Apr 23, 2024

Conversation

sywangyi
Copy link
Collaborator

…oder supports static shape.

for ex: nlpconnect/vit-gpt2-image-captioning

What does this PR do?

Fixes # (issue)

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

Sorry, something went wrong.

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
…oder supports static shape.

for ex: nlpconnect/vit-gpt2-image-captioning

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
@sywangyi
Copy link
Collaborator Author

@regisss @libinta please have a review.

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@sywangyi
Copy link
Collaborator Author

perf A100 Gaudi2
BF16 142ms 65ms
FP32 137ms 70ms

in image-to-text example:

python3 run_pipeline.py
--model_name_or_path nlpconnect/vit-gpt2-image-captioning
--image_path "https://ankur3107.github.io/assets/images/image-captioning-example.png"
--use_hpu_graphs
--bf16

Copy link
Collaborator

@libinta libinta left a comment

Choose a reason for hiding this comment

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

@sywangyi code looks ok. can you add a ci test case?

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
@sywangyi
Copy link
Collaborator Author

see if the test case is added correctly. I add pipeline test file. later it could be extended to other pipeline task, like text to speech.

@regisss regisss merged commit 8c8ec55 into main Apr 23, 2024
9 checks passed
@regisss regisss deleted the vision_encoder_decoder branch April 23, 2024 19:58
pi314ever pushed a commit to pi314ever/optimum-habana that referenced this pull request Apr 24, 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.

None yet

5 participants