-
Notifications
You must be signed in to change notification settings - Fork 185
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
Factor out the specific configurations to helper functions #286
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/286
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 7229c13 with merge base a7483f2 (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Summary: int4wo, int8wo, int8dyn, 8da4w are specific configurations for quantize function, we factor that out in the PR so they are easy to use Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags:
@@ -287,3 +297,103 @@ def filter_fn(module, fqn): | |||
_is_linear if filter_fn is None else filter_fn, | |||
) | |||
return model | |||
|
|||
def get_apply_8da4w_quant(groupsize=32): |
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.
should we make these private for now? I'm not sure if we want users to call these directly
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.
it's fine I think, I'm planning to use this in an example as well. what's the concern of this being public?
Summary: int4wo, int8wo, int8dyn, 8da4w are specific configurations for quantize function, we factor that out in the PR so they are easy to use Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags:
Summary:
int4wo, int8wo, int8dyn, 8da4w are specific configurations for quantize function, we factor that out in the PR so they are easy to use
Test Plan:
python test/quantization/test_quant_api.py
Reviewers:
Subscribers:
Tasks:
Tags: