-
Notifications
You must be signed in to change notification settings - Fork 144
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
Channelwise Quantization Tests #2283
Conversation
Satrat
commented
May 14, 2024
- Update e2e regression tests for channelwise scale and zero-point, added channelwise recipe
- Refactored 1.1b test to run on a nightly cadence, 15M will run on commit
LGTM, but the runner is now arguably not running any transformers jobs: Requested labels: k8s-eng-gpu-64G-v100-32G
Job defined at: neuralmagic/sparseml/.github/workflows/test-check.yaml@refs/pull/2283/merge
Waiting for a runner to pick up this job... |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks good and applies the framework correctly
Only suggestion would be organizing test_quantization
a little bit so that it's easier to follow (i.e private methods at the top, putting tearDown at the end, if the tests rely on inputs/outputs from a previous test, organized to follow that order and a quick comment/docstring to explain the flow)