Skip to content

Cortex-M quantizer: Use is_int8_activations helper in remaining checkers #17282

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.

Sign up for GitHub

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

Open
psiddh wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −8
Open

Cortex-M quantizer: Use is_int8_activations helper in remaining checkers #17282

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 2 additions & 8 deletions backends/cortex_m/quantizer/pattern_checkers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,10 +94,7 @@ def check_quantization_config(cls, quantization_config):
is_per_tensor = PatternCheck.is_per_tensor(
quantization_config.input_activation
) and PatternCheck.is_per_tensor(quantization_config.output_activation)
is_int8 = (
quantization_config.input_activation.dtype == torch.int8
and quantization_config.output_activation.dtype == torch.int8
)
is_int8 = cls.is_int8_activations(quantization_config)
return is_per_tensor and is_int8


Expand Down Expand Up @@ -128,10 +125,7 @@ def check_quantization_config(cls, quantization_config):
"""
Checks that the quantization config uses per-tensor int8 quantization.
"""
is_int8 = (
quantization_config.input_activation.dtype == torch.int8
and quantization_config.output_activation.dtype == torch.int8
)
is_int8 = cls.is_int8_activations(quantization_config)
return is_int8


Expand Down
Loading