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

Update cached models and benchmarks #705

Merged
merged 8 commits into from
Sep 27, 2024
Merged

Update cached models and benchmarks #705

merged 8 commits into from
Sep 27, 2024

Conversation

dacorvo
Copy link
Collaborator

@dacorvo dacorvo commented Sep 26, 2024

What does this PR do?

This modifies the cache population workflow to use the files corresponding to new models.

This also updates the benchmark in the documentation.

@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.

Copy link
Collaborator

@JingyaHuang JingyaHuang left a comment

Choose a reason for hiding this comment

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

LGTM, thanks for the updates!

@@ -27,7 +25,7 @@ def main():
export=True,
batch_size=batch_size,
sequence_length=seq_length,
auto_cast_type="fp16",
auto_cast_type="bf16",
Copy link
Collaborator

Choose a reason for hiding this comment

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

So it's now proven that bf16 is better?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

It actually does not make any difference as far as I can tell, and this seems to allow to load weights faster (because they are not converted).

Copy link
Member

@michaelbenayoun michaelbenayoun left a comment

Choose a reason for hiding this comment

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

LGTM

@dacorvo
Copy link
Collaborator Author

dacorvo commented Sep 26, 2024

I have made a small modification in the export code to always set fuse_qkv to True. This ruined my cached test models, so I had to reupload them with that change. I have some errors on docker tests that I don't understand. Let's wait for this new CI run ...

@dacorvo dacorvo merged commit 7180d48 into main Sep 27, 2024
7 of 9 checks passed
@dacorvo dacorvo deleted the update_benchmarks branch September 27, 2024 09:06
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.

4 participants