-
Notifications
You must be signed in to change notification settings - Fork 199
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
Fix (proxy): clean-up #1011
Fix (proxy): clean-up #1011
Conversation
|
||
class BiasQuantProxyFromInjectorBase(ParameterQuantProxyFromInjector, BiasQuantProxyProtocol, ABC): | ||
|
||
def __init__(self, quant_layer: nn.Module, quant_injector: Injector) -> None: | ||
super().__init__(quant_layer, quant_injector) | ||
self._cached_bias = None | ||
self.cache_inference_quant_bias = False | ||
self.cache_inference_quant_bias_metadata_only = False | ||
self.requires_input_scale = self.quant_injector.requires_input_scale |
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.
The previous solution is not compile-friendly (even though this PR is not about compile).
Happy to restore this to previous state.
1b9d4d7
to
12bf43f
Compare
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.
Fix export mode for weights. I might have a think about the act proxy forward pass logic.
Otherwise, LGTM!
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.
See note about the tuple
checks.
No description provided.