-
Notifications
You must be signed in to change notification settings - Fork 251
add subclass based method for inference #2132
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
base: drisspg/stack/49
Are you sure you want to change the base?
Conversation
stack-info: PR: #2132, branch: drisspg/stack/50
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2132
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 34fa252 with merge base 868afa6 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
93067f0
to
34fa252
Compare
@@ -53,4 +53,5 @@ | |||
"swizzle", | |||
"testing", | |||
"ops", | |||
"quantization", |
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.
why is swizzle top level?
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.
Thats a really good question
return f"in_features={self.weight.shape[1]}, out_features={self.weight.shape[0]}, weight={repr(self.weight)}" | ||
|
||
|
||
def _input_activation_quant_func_mxfp( |
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.
nit: add to safe global for serialization?
ao/torchao/quantization/quant_api.py
Line 1993 in 58502e3
torch.serialization.add_safe_globals( |
Sorry, this should be a draft still, I am just dumping all my commits for now |
Stacked PRs:
add subclass based method for inference