Update base for Update on "[ET-VK] Adding push constant and ubo verison of select and slice ops to improve memory and performance."

Adding push constant and ubo verison of select and slice ops to improve memory and performance.
*   Updated `transfer_buffer.yaml` and `transfer_texture.yaml` to include `UBO_PARAMS` parameter and generate variants for `select` and `slice` ops with UBO parameters.
*   Updated `transfer.glsl` to generate ubo and push constant versions of `select` and `slice` ops with UBO parameters.

Differential Revision: [D78095262](https://our.internmc.facebook.com/intern/diff/D78095262/)

[ghstack-poisoned]

Author: trivedivivek

.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 }}

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/tosa_quant_utils.py

@@ -146,7 +146,15 @@ def quantize_value(self, x: torch.Tensor | float) -> Tensor:
         x = x.to(torch.float32)
         if self.per_channel:
             q_op = exir_ops.edge.quantized_decomposed.quantize_per_channel.default
-            args = (x, self.scale, self.zp, self.axis, self.qmin, self.qmax, self.dtype)
+            args = (
+                x,
+                torch.tensor(self.scale),
+                torch.tensor(self.zp),
+                self.axis,
+                self.qmin,
+                self.qmax,
+                self.dtype,
+            )
         else:
             q_op = exir_ops.edge.quantized_decomposed.quantize_per_tensor.default
             args = (x, self.scale, self.zp, self.qmin, self.qmax, self.dtype)  # type: ignore[assignment]
@@ -162,8 +170,8 @@ def dequantize_value(self, qx: torch.Tensor) -> torch.Tensor:
             dq_op = exir_ops.edge.quantized_decomposed.dequantize_per_channel.default
             args = (
                 qx,
-                self.scale,
-                self.zp,
+                torch.tensor(self.scale),
+                torch.tensor(self.zp),
                 self.axis,
                 self.qmin,
                 self.qmax,

backends/cadence/aot/TARGETS

@@ -184,6 +184,21 @@ python_library(
     ],
 )
 
+python_library(
+    name = "program_builder",
+    srcs = [
+        "program_builder.py",
+    ],
+    typing = True,
+    deps = [
+        ":graph_builder",
+        "fbcode//caffe2:torch",
+        "fbcode//executorch/exir:lib",
+        "fbcode//executorch/exir:pass_base",
+        "fbcode//executorch/exir/verification:verifier",
+    ],
+)
+
 python_library(
     name = "fuse_ops",
     srcs = [
@@ -508,6 +523,7 @@ python_unittest(
         ":typing_stubs",
         ":ops_registrations",
         ":pass_utils",
+        ":program_builder",
         "//caffe2:torch",
         "//executorch/exir:memory",
         "//executorch/exir/dialects:lib",