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

fp8 quantization for inference. #1316

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Conversation

jwyang-google
Copy link
Collaborator

@jwyang-google jwyang-google commented Feb 26, 2025

Description

Start with a short description of what the PR does and how this is a change from
the past.

The rest of the description includes relevant details and context, examples:

  • why is this change being made,
  • the problem being solved and any relevant context,
  • why this is a good solution,
  • some information about the specific implementation,
  • shortcomings of the solution and possible future improvements.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Notice 1 Once all tests pass, the "pull ready" label will automatically be assigned. This label is used
for administrative purposes. Please do not add it manually.

Notice 2 For external contributions, our settings currently require an approval from a MaxText maintainer to trigger CI tests.

Tests

Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

Before submitting this PR, please make sure (put X in square brackets):

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have run end-to-end tests tests and provided workload links above if applicable.
  • I have made or will make corresponding changes to the doc if needed.

Copy link

Important

The terms of service for this installation has not been accepted. Please ask the Organization owners to visit the Gemini Code Assist Admin Console to sign it.

@vipannalla
Copy link
Collaborator

@singh-mitali, can you take a look at these quantization changes?

@@ -496,6 +521,8 @@ def einsum_fn_with_rhs_qtensor(
def einsum_fn_with_rhs_qtensor_and_dequant(self, value):
return self.einsum_fn_with_rhs_qtensor(
value,
lhs_dequant_mode=aqt_config.DequantMode.THIS_INPUT,
Copy link
Collaborator

Choose a reason for hiding this comment

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

Why was this change required?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Adding this would make it perform better with fp8. int8 performance stays the same.

Copy link
Collaborator

@singh-mitali singh-mitali Feb 26, 2025

Choose a reason for hiding this comment

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

Can we make this a separate function or pass a flag.

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