Skip to content

Update remaining callsites to not use pt2e quant API from pytorch #16380

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

Merged
meta-codesync merged 1 commit into from
Dec 24, 2025
+6 −4
Merged

Update remaining callsites to not use pt2e quant API from pytorch #16380

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions backends/nxp/quantizer/neutron_quantizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,6 @@
no_outside_users,
)
from torch import fx
from torch.ao.quantization.quantizer.utils import _annotate_output_qspec
from torchao.quantization.pt2e import (
FakeQuantize,
FusedMovingAvgObsFakeQuantize,
Expand All @@ -62,6 +61,7 @@
MovingAverageMinMaxObserver,
)
from torchao.quantization.pt2e.quantizer import (
annotate_output_qspec,
ComposableQuantizer,
DerivedQuantizationSpec,
OperatorConfig,
Expand Down Expand Up @@ -338,7 +338,7 @@ def _annotate_inputs(self, model: fx.GraphModule):
continue

if node.op == "placeholder" and len(node.users) > 0:
_annotate_output_qspec(node, act_qspec(self.is_qat))
annotate_output_qspec(node, act_qspec(self.is_qat))
self._mark_input_node_as_annotated(node)

def validate(self, model: torch.fx.GraphModule) -> None:
Expand Down
6 changes: 4 additions & 2 deletions backends/nxp/quantizer/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,15 @@
import torch
from torch import fx
from torch._ops import OpOverload
from torch.ao.quantization import move_exported_model_to_eval
from torch.export import ExportedProgram
from torch.fx.passes.utils.source_matcher_utils import (
check_subgraphs_connected,
SourcePartition,
)
from torchao.quantization.pt2e import ObserverOrFakeQuantize
from torchao.quantization.pt2e import (
move_exported_model_to_eval,
ObserverOrFakeQuantize,
)
from torchao.quantization.pt2e.quantize_pt2e import (
convert_pt2e,
prepare_pt2e,
Expand Down
Loading