Update base for Update on "Export lora weights to sep file"

Differential Revision: [D83777195](https://our.internmc.facebook.com/intern/diff/D83777195/)

[ghstack-poisoned]

Author: lucylq

.ci/scripts/test_backend.sh

@@ -1,6 +1,7 @@
 #!/usr/bin/env bash
 # Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
+# Copyright 2025 Arm Limited and/or its affiliates.
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
@@ -58,6 +59,12 @@ fi
 if [[ "$FLOW" == *arm* ]]; then
     # Setup ARM deps.
     .ci/scripts/setup-arm-baremetal-tools.sh
+
+    if [[ "$FLOW" == *ethos_u* ]]; then
+        # Prepare a test runner binary that can run on the Corstone-3x0 FVPs
+        backends/arm/scripts/build_executorch.sh
+        backends/arm/test/setup_testing.sh
+    fi
 fi
 
 if [[ $IS_MACOS -eq 1 ]]; then

.github/workflows/android-release-artifacts.yml

@@ -90,6 +90,10 @@ jobs:
         fi
 
         FLAVOR="${{ inputs.flavor }}"
+        if [ ! -z "$FLAVOR" ]; then
+          GRADLE_ARGS+=" -Dflavor=${FLAVOR}"
+        fi
+
         if [[ "$FLAVOR" == "vulkan" || -z "$FLAVOR" ]]; then
           curl -O https://sdk.lunarg.com/sdk/download/1.4.321.1/linux/vulkansdk-linux-x86_64-1.4.321.1.tar.xz
           tar xf vulkansdk-linux-x86_64-1.4.321.1.tar.xz -C /tmp

.github/workflows/test-backend-arm.yml

@@ -23,7 +23,7 @@ jobs:
     uses: ./.github/workflows/_test_backend.yml
     with:
       backend: arm
-      flows: '["arm_tosa"]'
+      flows: '["arm_tosa_fp", "arm_tosa_int", "arm_ethos_u55", "arm_ethos_u85"]'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout: 120
       run-linux: true

CODEOWNERS

@@ -14,6 +14,7 @@
 /backends/transforms @kimishpatel
 /backends/vulkan @SS-JIA
 /backends/xnnpack @digantdesai @mcr229
+/backends/nxp @robert-kalmar
 
 /devtools @Gasoonjia
 
@@ -33,6 +34,7 @@
 /examples/qualcomm @cccclai
 /examples/selective_build @lucylq @larryliu0820 @JacobSzwejbka
 /examples/xnnpack @digantdesai @mcr229
+/examples/nxp @robert-kalmar
 
 /exir/backend @cccclai @kimishpatel @JacobSzwejbka
 /exir @JacobSzwejbka @larryliu0820

backends/arm/TARGETS

@@ -106,3 +106,17 @@ runtime.python_library(
         "//caffe2:torch",
     ]
 )
+runtime.python_library(
+    name = "_factory",
+    srcs = [
+        "util/_factory.py"
+    ],
+    deps = [
+        ":ethosu",
+        ":vgf",
+        ":arm_compile_spec",
+        "//executorch/backends/arm/quantizer:lib",
+        "//executorch/exir/backend:operator_support",
+        "//executorch/exir/backend:compile_spec_schema",
+    ]
+)

backends/arm/operator_support/convolution_support.py

@@ -2,6 +2,12 @@
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
+"""Declare operator support for ``aten.convolution`` in TOSA.
+
+Provide general checks and hardware-specific constraints (e.g., U55 subset) for
+convolution nodes prior to delegation to the TOSA backend.
+
+"""
 
 from typing import cast
 
@@ -18,15 +24,24 @@
 
 @register_tosa_support_check
 class ConvolutionSupported(SupportedTOSAOperatorCheck):
+    """Provide TOSA support check for convolutions."""
+
     targets = [exir_ops.edge.aten.convolution.default]
 
     tosa_specs = [
         TosaSpecification.create_from_string("TOSA-1.0+INT"),
         TosaSpecification.create_from_string("TOSA-1.0+FP"),
     ]
 
-    def is_node_tosa_supported(self, node: fx.Node, tosa_spec: TosaSpecification):
+    def is_node_tosa_supported(
+        self, node: fx.Node, tosa_spec: TosaSpecification
+    ) -> bool:
+        """Return True if the node is supported by TOSA.
 
+        Reject transposed convolutions and convolutions with non-zero output
+        padding. Apply additional hardware-specific constraints for U55.
+
+        """
         # Not implemented
         transposed = cast(bool, node.args[6])
         output_padding = cast(list[int], node.args[7])
@@ -46,9 +61,19 @@ def is_node_tosa_supported(self, node: fx.Node, tosa_spec: TosaSpecification):
         else:
             return True
 
-    def _is_node_supported_u55(self, node: fx.Node):
-        """Hardware constraints for Ethos-U-55 case, Vela 4.2.0 (25.02 release)"""
+    def _is_node_supported_u55(self, node: fx.Node) -> bool:
+        """Enforce Ethos-U55-specific constraints (Vela 4.2.0).
+
+        Check channel dimensions, kernel sizes, and stride/pad/dilation
+        combinations permitted on U55.
 
+        Args:
+            node (fx.Node): Convolution node to validate.
+
+        Returns:
+            bool: True if supported; otherwise, False.
+
+        """
         shape_in = cast(torch.Tensor, node.all_input_nodes[0].meta["val"]).shape
         shape_out = node.meta["val"].shape
         kernel = cast(fx.Node, node.args[1]).meta["val"].shape
@@ -98,13 +123,17 @@ def _is_node_supported_u55(self, node: fx.Node):
         return True
 
     def _stride_condition(self, node: fx.Node) -> bool:
-        """This condition is somewhat complex but boils down
-        to not supporting stride > 3, unless we have some special conditions.
-        This condition is a simplified, relaxed version of the hardware constraint,
-        since the actual constraint requires information not available
-        here (without a lot of work).
+        """Check a simplified stride/padding/dilation constraint.
+
+        Disallow strides greater than 3 unless there is no padding and the
+        dilation is 1. For 3D convolutions, enforce ``stride_z <= 1``.
+
+        Args:
+            node (fx.Node): Convolution node to evaluate.
+
+        Returns:
+            bool: True if the condition is satisfied.
 
-        This means that we might accept ops that are not actually supported.
         """
         strides = cast(list[int], node.args[3])
         has_padding = any(pad > 0 for pad in cast(list[int], node.args[4]))

backends/arm/operator_support/pool_2d_support.py

@@ -2,6 +2,12 @@
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
+"""Provide TOSA support checks for 2D pooling.
+
+Validate ``avg_pool2d`` and ``max_pool2d_with_indices`` against U55 profile
+constraints including kernel size, stride, padding, and dimensionality.
+
+"""
 
 from typing import cast
 
@@ -20,16 +26,48 @@
 
 
 def kernel_check(kernel: tuple[int, int]) -> bool:
+    """Check if kernel size is within U55 constraints.
+
+    Checks that ``kernel_x * kernel_y`` is in ``[1, 65536]`` and
+    ``kernel_y`` is in ``[1, 256]`` as required by the U55 profile.
+
+    Args:
+        kernel (tuple[int, int]): Kernel height and width ``(kh, kw)``.
+
+    Returns:
+        bool: True if the kernel passes validation.
+
+    """
     if not (1 <= kernel[0] * kernel[1] <= 65536):
         return False
     return 1 <= kernel[1] <= 256
 
 
 def stride_check(strides: tuple[int, int]) -> bool:
+    """Check if strides are within U55 constraints.
+
+    Args:
+        strides (tuple[int, int]): Vertical and horizontal strides.
+
+    Returns:
+        bool: True if each stride is in ``[1, 3]``.
+
+    """
     return all(1 <= stride <= 3 for stride in strides)
 
 
 def dim_check(shape=torch.Size) -> bool:
+    """Check if non-batch dims are within U55 constraints.
+
+    Verifies that all dimensions except batch are in ``[1, 65536]``.
+
+    Args:
+        shape (torch.Size): Input tensor shape.
+
+    Returns:
+        bool: True if all checked dimensions pass.
+
+    """
     check = True
     for dim in shape[1:]:
         check &= 1 <= dim <= 65536
@@ -38,6 +76,13 @@ def dim_check(shape=torch.Size) -> bool:
 
 @register_tosa_support_check
 class AvgPool2dSupported(SupportedTOSAOperatorCheck):
+    """Provide TOSA support checks for ``aten.avg_pool2d``.
+
+    Applies additional constraints when targeting the U55 subset, including
+    limits on kernel size, stride, padding behavior, and tensor ranks.
+
+    """
+
     targets = [
         exir_ops.edge.aten.avg_pool2d.default,
     ]
@@ -48,6 +93,12 @@ class AvgPool2dSupported(SupportedTOSAOperatorCheck):
     ]
 
     def is_node_tosa_supported(self, node: fx.Node, tosa_spec: TosaSpecification):
+        """Return True if ``avg_pool2d`` satisfies U55 constraints.
+
+        Computes the effective TOSA padding (depending on ``count_include_pad``
+        and ``divisor_override``) and validates kernel, stride, and shape limits.
+
+        """
         if not tosa_spec.is_U55_subset:
             return True
 
@@ -115,6 +166,13 @@ def is_node_tosa_supported(self, node: fx.Node, tosa_spec: TosaSpecification):
 
 @register_tosa_support_check
 class MaxPool2dSupported(SupportedTOSAOperatorCheck):
+    """Provide TOSA support checks for ``aten.max_pool2d_with_indices``.
+
+    Applies additional constraints when targeting the U55 subset, including
+    limits on kernel size, stride, and tensor ranks.
+
+    """
+
     targets = [
         exir_ops.edge.aten.max_pool2d_with_indices.default,
     ]
@@ -125,6 +183,9 @@ class MaxPool2dSupported(SupportedTOSAOperatorCheck):
     ]
 
     def is_node_tosa_supported(self, node: fx.Node, tosa_spec: TosaSpecification):
+        """Return True if ``max_pool2d_with_indices`` satisfies U55
+        constraints.
+        """
         if not tosa_spec.is_U55_subset:
             return True
 

backends/arm/operators/op_repeat.py

@@ -44,7 +44,7 @@ def define_node(
         validate_valid_dtype(
             self.target,
             [inputs[0], output],
-            [ts.DType.INT8, ts.DType.INT32, ts.DType.FP32],
+            [ts.DType.INT8, ts.DType.INT32, ts.DType.INT16, ts.DType.FP32],
             output.tosa_spec,
         )
 

backends/arm/quantizer/quantization_annotator.py

@@ -6,7 +6,7 @@
 import logging
 import operator
 from dataclasses import dataclass
-from typing import Callable, List, Optional, Sequence
+from typing import Callable, cast, List, Optional, Sequence
 
 import torch
 import torch.fx
@@ -137,11 +137,18 @@ def _is_large_scalar(node: Node, gm: torch.fx.GraphModule):
     node since histc op (in HistogramObserver) only works for values up to certain upper
     bound.
     """
+    HISTC_UPPER_BOUND = 3.4028235e15
     if node.op == "get_attr" and isinstance(node.target, str):
         tensor = _get_node_target(gm, node.target)
         # torch.histc works until this upper bound
-        HISTC_UPPER_BOUND = 3.4028235e15
         return tensor.numel() == 1 and abs(tensor.item()) > HISTC_UPPER_BOUND
+    if node.op == "call_function" and node.target in (
+        torch.ops.aten.full.default,
+        torch.ops.aten.full,
+        torch.ops.aten.fill_.Scalar,
+    ):
+        fill_value = cast(float, node.args[1])
+        return abs(fill_value) > HISTC_UPPER_BOUND
     return False
 
 
@@ -358,9 +365,6 @@ def _match_pattern(
     torch.ops.aten.permute_copy.default,
     torch.ops.aten.avg_pool2d.default,
     torch.ops.aten.max_pool2d.default,
-    torch.ops.aten.full.default,
-    torch.ops.aten.full,
-    torch.ops.aten.fill_.Scalar,
     torch.ops.aten.flatten.using_ints,
     torch.ops.aten.dropout.default,
     torch.ops.aten.dropout_.default,
@@ -518,9 +522,6 @@ def any_or_hardtanh_min_zero(n: Node):
         ]
         quant_properties.quant_output = _QuantProperty(0, shared_qspec)  # type: ignore[arg-type]
     elif node.target in _one_to_one_shared_input_or_input_act_qspec:
-        if not isinstance(node.args[0], Node):
-            return None
-
         input_qspec = (
             SharedQuantizationSpec(node.args[0])  # type: ignore[arg-type]
             if is_output_annotated(node.args[0])  # type: ignore
@@ -578,7 +579,12 @@ def any_or_hardtanh_min_zero(n: Node):
             ),
         ]
         quant_properties.quant_output = None
-    elif node.target in [torch.ops.aten.scalar_tensor.default]:
+    elif node.target in [
+        torch.ops.aten.scalar_tensor.default,
+        torch.ops.aten.full.default,
+        torch.ops.aten.full,
+        torch.ops.aten.fill_.Scalar,
+    ]:
         quant_properties.quant_inputs = []
         quant_properties.quant_output = _QuantProperty(0, output_act_qspec)
     elif node.target in [operator.getitem]:

backends/arm/test/TARGETS

@@ -1,3 +1,8 @@
+# Copyright 2025 Arm Limited and/or its affiliates.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
 load("@fbsource//xplat/executorch/build:runtime_wrapper.bzl", "runtime")
 load(":targets.bzl", "define_arm_tests")
 
@@ -58,6 +63,7 @@ runtime.python_library(
         "//executorch/backends/arm/quantizer:lib",
         "//executorch/backends/arm/tosa:mapping",
         "//executorch/backends/arm:vgf",
+        "//executorch/backends/arm:_factory",
         "//executorch/devtools/backend_debug:delegation_info",
         "//executorch/exir/backend:operator_support",
         "fbsource//third-party/pypi/tabulate:tabulate",