Update base for Update on "Remove usages of 'to_edge_with_preserve_ops'"

Replace with to_edge.

Differential Revision: [D78311705](https://our.internmc.facebook.com/intern/diff/D78311705/)

[ghstack-poisoned]

Author: lucylq

.ci/docker/ci_commit_pins/pytorch.txt

@@ -1 +1 @@
-7cda4017ddda554752e89069ae205be5e8388f59
+90f1e7bed15ca5e48c61c5b6dc5ad4810524f82f

.ci/scripts/unittest-buck2.sh

@@ -10,7 +10,7 @@ set -eux
 # TODO: can't query cadence & vulkan backends
 # TODO: can't query //kernels/prim_ops because of non-buckified stuff in OSS.
 buck2 query "//backends/apple/... + //backends/example/... + \
-//backends/mediatek/... + //backends/test/... + //backends/transforms/... + \
+//backends/mediatek/... + //backends/transforms/... + \
 //backends/xnnpack/... + //configurations/... + //kernels/aten/... + \
 //kernels/optimized/... + //kernels/portable/... + //kernels/quantized/... + \
 //kernels/test/... + //runtime/... + //schema/... + //test/... + //util/..."

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

@@ -47,15 +47,13 @@ jobs:
     name: build-aar
     needs: check-if-aar-exists
     if: ${{ !github.event.pull_request.head.repo.fork }}
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@release/2.7
+    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     secrets: inherit
     permissions:
       id-token: write
       contents: read
     with:
       secrets-env: EXECUTORCH_MAVEN_SIGNING_KEYID EXECUTORCH_MAVEN_SIGNING_PASSWORD EXECUTORCH_MAVEN_CENTRAL_PASSWORD EXECUTORCH_MAVEN_CENTRAL_USERNAME EXECUTORCH_MAVEN_SIGNING_GPG_KEY_CONTENTS
-      # As this job has access to Maven credential, run this on a fresh ephemeral runner
-      runner: ephemeral.linux.2xlarge
       docker-image: executorch-ubuntu-22.04-clang12-android
       submodules: 'recursive'
       ref: ${{ github.sha }}

.github/workflows/trunk.yml

@@ -197,7 +197,7 @@ jobs:
       docker-image: executorch-ubuntu-22.04-arm-sdk
       submodules: 'recursive'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
-      timeout: 90
+      timeout: 120
       script: |
         # The generic Linux job chooses to use base env, not the one setup by the image
         CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")

backends/arm/quantizer/arm_quantizer.py

@@ -60,7 +60,7 @@
 
 @functools.lru_cache
 def get_symmetric_quantization_config(
-    is_per_channel: bool = False,
+    is_per_channel: bool = True,
     is_qat: bool = False,
     is_dynamic: bool = False,
     act_qmin: int = -128,

backends/arm/scripts/mlsdk_utils.sh

@@ -0,0 +1,121 @@
+#!/usr/bin/env bash
+# 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.
+
+set -euo pipefail
+
+# TODO
+mlsdk_manifest_url=""
+
+script_dir=$(cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd)
+
+source ${script_dir}/utils.sh
+
+usage() { echo "Usage: $0 [-u <mlsdk-manifest-url>]" 1>&2; exit 1; }
+
+while getopts ":u:" opt; do
+    case "${opt}" in
+        u)
+            mlsdk_manifest_url=${OPTARG}
+            ;;
+        *)
+            usage
+            ;;
+    esac
+done
+
+function download_ai_mlsdk_manifest() {
+    local _dada_dir="$1"
+
+    if [[ -z "${_dada_dir}" ]]; then
+        echo "Error: _dada_dir parameter missing?"
+        return 1
+    fi
+
+    if [[ -z "${mlsdk_manifest_url}" ]]; then
+        echo "Error: mlsdk_manifest_url parameter missing?"
+        return 1
+    fi
+
+    if [[ ! -d "${_dada_dir}" ]]; then
+        mkdir -p "$_dada_dir"
+        pushd "$_dada_dir" || exit 1
+
+        curl https://storage.googleapis.com/git-repo-downloads/repo > repo
+        chmod u+x repo
+        ./repo init  --no-repo-verify --depth=1  --manifest-url  ${mlsdk_manifest_url} -g model-converter,emulation-layer,vgf-library
+        ./repo sync
+
+        popd
+    fi
+}
+
+function setup_model_converter() {
+    local work_dir="$1"
+    local manifest_dir="$2"
+    local enable_vgf_lib="$3"
+    local enable_emulation_layer="$4"
+
+    if [[ -z "$work_dir" ]]; then
+        echo "Error: work_dir parameter is required."
+        return 1
+    fi
+
+    if [[ -z "$manifest_dir" ]]; then
+        echo "Error: manifest_dir parameter is required."
+        return 1
+    fi
+
+    mkdir -p "$work_dir"
+    pushd "$work_dir" || exit 1
+
+    download_ai_mlsdk_manifest ${manifest_dir}
+
+    pushd "$manifest_dir"
+
+    # model-converter
+    # TODO: Remove macOS patch after mlsdk fully supports macOS
+    if [[ "$(uname)" == "Darwin" ]]; then
+    sed -i '' '/^ *print(f"Unsupported host platform/ i\
+            if system == "Darwin":\
+                # Use default Apple toolchain (Clang) on macOS\
+                return True\
+\
+' sw/model-converter/scripts/build.py
+    fi
+    python sw/model-converter/scripts/build.py -j$(nproc)
+
+    # libvgf
+    if [[ "${enable_vgf_lib}" -eq 1 ]]; then
+    # TODO: Remove macOS patch after mlsdk fully supports macOS
+        if [[ "$(uname)" == "Darwin" ]]; then
+    sed -i '' '/^ *print(f"ERROR: Unsupported host platform/ i\
+            if system == "Darwin":\
+                # Use default Apple toolchain (Clang) on macOS\
+                return True\
+\
+' sw/vgf-lib/scripts/build.py
+        fi
+        python sw/vgf-lib/scripts/build.py -j$(nproc)
+    fi
+
+    # emu layer
+    if [[ "${enable_emulation_layer}" -eq 1 ]]; then
+        pushd sw/emulation-layer
+        cmake -B build                                               \
+            -DGLSLANG_PATH=../../dependencies/glslang                \
+            -DSPIRV_CROSS_PATH=../../dependencies/SPIRV-Cross        \
+            -DSPIRV_HEADERS_PATH=../../dependencies/SPIRV-Headers    \
+            -DSPIRV_TOOLS_PATH=../../dependencies/SPIRV-Tools        \
+            -DVULKAN_HEADERS_PATH=../../dependencies/Vulkan-Headers
+        cmake --build build
+        popd
+    fi
+
+    popd
+}
+
+#setup_model_converter() $1
+# `"$manifest_dir"'

backends/arm/test/common.py

@@ -18,6 +18,7 @@
     arm_executor_runner_exists,
     corstone300_installed,
     corstone320_installed,
+    model_converter_installed,
 )
 from executorch.backends.arm.tosa_specification import TosaSpecification
 from executorch.exir.backend.compile_spec_schema import CompileSpec
@@ -245,6 +246,13 @@ def get_u85_compile_spec_unbuilt(
 )
 """Xfails a test if Corsone320 FVP is not installed, or if the executor runner is not built"""
 
+SkipIfNoModelConverter = pytest.mark.skipif(
+    condition=not (model_converter_installed()),
+    raises=FileNotFoundError,
+    reason="Did not find model-converter on path",
+)
+"""Xfails a test if model-converter is not installed"""
+
 xfail_type = str | tuple[str, type[Exception]]
 
 

backends/arm/test/misc/test_bn_relu_folding_qat.py

@@ -59,7 +59,9 @@ def test_qat_tosa_BI(model: torch.nn.Module):
         "quantize",
         Quantize(
             quantizer=quantizer,
-            quantization_config=get_symmetric_quantization_config(is_qat=True),
+            quantization_config=get_symmetric_quantization_config(
+                is_qat=True, is_per_channel=False
+            ),
             is_qat=True,
         ),
     )

backends/arm/test/ops/test_add.py

@@ -7,8 +7,6 @@
 
 from typing import Tuple
 
-import pytest
-
 import torch
 from executorch.backends.arm.arm_backend import get_tosa_spec
 from executorch.backends.arm.quantizer import arm_quantizer
@@ -190,7 +188,7 @@ def test_add_tensor_u85_BI_2(test_data: input_t2):
 
 
 @common.parametrize("test_data", Add.test_data)
-@pytest.mark.skip(reason="Model converter not yet made available")
+@common.SkipIfNoModelConverter
 def test_add_tensor_vgf_fp(test_data: input_t1):
     pipeline = VgfPipeline[input_t1](
         Add(), test_data(), aten_op, exir_op, tosa_version="TOSA-1.0+FP"
@@ -199,7 +197,7 @@ def test_add_tensor_vgf_fp(test_data: input_t1):
 
 
 @common.parametrize("test_data", Add.test_data)
-@pytest.mark.skip(reason="Model converter not yet made available")
+@common.SkipIfNoModelConverter
 def test_add_tensor_vgf_int(test_data: input_t1):
     pipeline = VgfPipeline[input_t1](
         Add(),

backends/arm/test/ops/test_multihead_attention.py

@@ -53,7 +53,14 @@ def test_multihead_attention_tosa_MI(test_data: input_t1):
 )
 def test_multihead_attention_tosa_BI(test_data):
     test_data, module = test_data()
-    pipeline = TosaPipelineBI(module, (*test_data, *test_data, *test_data), [], [])
+    pipeline = TosaPipelineBI(
+        module,
+        (*test_data, *test_data, *test_data),
+        [],
+        [],
+        # TODO: Per-channel quantization is broken (MLETORCH-1144)
+        per_channel_quantization=False,
+    )
     pipeline.run()
 
 
@@ -72,6 +79,8 @@ def test_multihead_attention_u55_BI(test_data: input_t1):
         [],
         use_to_edge_transform_and_lower=True,
         run_on_fvp=True,
+        # TODO: Per-channel quantization is broken (MLETORCH-1144)
+        per_channel_quantization=False,
     )
     pipeline.pop_stage("check_count.exir")
     pipeline.run()
@@ -92,5 +101,7 @@ def test_multihead_attention_u85_BI(test_data: input_t1):
         [],
         use_to_edge_transform_and_lower=True,
         run_on_fvp=True,
+        # TODO: Per-channel quantization is broken (MLETORCH-1144)
+        per_channel_quantization=False,
     )
     pipeline.run()