From a3e01beef11567f9b8123a08b1763baa7bb58704 Mon Sep 17 00:00:00 2001
From: Jerry Zhang <jerryzh@meta.com>
Date: Tue, 23 Dec 2025 19:47:51 -0800
Subject: [PATCH] Update remaining callsites to not use pt2e quant API from
 pytorch (#16380)

Summary:
X-link: https://github.com/facebookexternal/vizard/pull/18

X-link: https://github.com/meta-pytorch/tnt/pull/1041


X-link: https://github.com/pytorch/ao/pull/3535

We removed pt2e quant code from D87958849, updating some remaining callsites to use torchao or executorch

Reviewed By: jainapurva

Differential Revision: D89744472
---
 backends/nxp/quantizer/neutron_quantizer.py | 4 ++--
 backends/nxp/quantizer/utils.py             | 6 ++++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/backends/nxp/quantizer/neutron_quantizer.py b/backends/nxp/quantizer/neutron_quantizer.py
index b9186884d5e..1f1b6b88846 100644
--- a/backends/nxp/quantizer/neutron_quantizer.py
+++ b/backends/nxp/quantizer/neutron_quantizer.py
@@ -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,
@@ -62,6 +61,7 @@
     MovingAverageMinMaxObserver,
 )
 from torchao.quantization.pt2e.quantizer import (
+    annotate_output_qspec,
     ComposableQuantizer,
     DerivedQuantizationSpec,
     OperatorConfig,
@@ -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:
diff --git a/backends/nxp/quantizer/utils.py b/backends/nxp/quantizer/utils.py
index 6dc58e8114a..459f31ec7da 100644
--- a/backends/nxp/quantizer/utils.py
+++ b/backends/nxp/quantizer/utils.py
@@ -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,