Update on "Export a lora model"

^

Program+data combined currently, using the lora linear definition.
Issue: #9580

Differential Revision: [D75153377](https://our.internmc.facebook.com/intern/diff/D75153377/)

[ghstack-poisoned]

Author: lucylq

.ci/docker/build.sh

@@ -43,6 +43,10 @@ case "${IMAGE_NAME}" in
     ARM_SDK=yes
     CLANG_VERSION=12
     ;;
+  executorch-ubuntu-22.04-zephyr-sdk)
+    ZEPHYR_SDK=yes
+    GCC_VERSION=11
+    ;;
   executorch-ubuntu-22.04-qnn-sdk)
     QNN_SDK=yes
     CLANG_VERSION=12
@@ -87,6 +91,7 @@ docker build \
   --build-arg "LINTRUNNER=${LINTRUNNER:-}" \
   --build-arg "BUILD_DOCS=${BUILD_DOCS}" \
   --build-arg "ARM_SDK=${ARM_SDK:-}" \
+  --build-arg "ZEPHYR_SDK=${ZEPHYR_SDK:-}" \
   --build-arg "QNN_SDK=${QNN_SDK:-}" \
   --build-arg "MEDIATEK_SDK=${MEDIATEK_SDK:-}" \
   --build-arg "ANDROID_NDK_VERSION=${ANDROID_NDK_VERSION:-}" \

.ci/docker/common/install_zephyr.sh

@@ -0,0 +1,92 @@
+
+#!/bin/bash
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+set -ex
+
+# Double check if the NDK version is set
+[ -n "${ZEPHYR_SDK}" ]
+
+install_prerequiresites() {
+    rm /var/lib/dpkg/info/libc-bin.*
+    apt-get clean
+    apt-get -y update
+    apt-get install -y libc-bin
+    apt-get -y update
+    apt-get clean
+    apt-get install --no-install-recommends -y dos2unix
+    apt-get install --no-install-recommends -y ca-certificates
+    apt-get install -y --reinstall libc-bin
+    apt-get install --no-install-recommends -y file
+    apt-get install --no-install-recommends -y locales
+    apt-get install --no-install-recommends -y git
+    apt-get install --no-install-recommends -y build-essential
+    apt-get install --no-install-recommends -y cmake
+    apt-get install --no-install-recommends -y ninja-build gperf
+    apt-get install --no-install-recommends -y device-tree-compiler
+    apt-get install --no-install-recommends -y wget
+    apt-get install --no-install-recommends -y curl
+    apt-get install --no-install-recommends -y xz-utils
+    apt-get install --no-install-recommends -y dos2unix
+    apt-get install --no-install-recommends -y vim
+    apt-get install --no-install-recommends -y nano
+    apt-get install --no-install-recommends -y mc
+    apt-get install --no-install-recommends -y openssh-server
+    apt-get install -y gdb
+
+    # Zephyr SDK relies on python 3.12
+    apt install software-properties-common -y
+    add-apt-repository ppa:deadsnakes/ppa -y
+    apt update
+    apt install -y python3.12 python3.12-dev python3.12-venv python3-pip
+    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 1
+
+    # Upgrade cmake ot 3.24
+    apt update
+    apt install cmake
+    apt install software-properties-common lsb-release
+    apt update
+    test -f /usr/share/doc/kitware-archive-keyring/copyright || \
+        wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
+    "deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ $(lsb_release -cs) main" | tee /etc/apt/sources.list.d/kitware.list > /dev/null
+    apt update
+    apt install cmake
+
+    # Install additional required software for Zephyr
+    apt install --no-install-recommends -y ccache \
+        dfu-util \
+        python3-setuptools \
+        python3-tk \
+        python3-wheel \
+        make \
+        gcc \
+        libsdl2-dev \
+        libmagic1 \
+        xterm \
+        telnet \
+        net-tools
+    apt install --no-install-recommends -y gcc-multilib g++-multilib
+    apt-get clean -y
+    apt-get autoremove --purge -y
+    rm -rf /var/lib/apt/lists/*
+    wget https://apt.kitware.com/kitware-archive.sh && \
+        chmod +x kitware-archive.sh && \
+        ./kitware-archive.sh && \
+        rm -f kitware-archive.sh
+    useradd -d /home/zephyruser -m -s /bin/bash zephyruser
+}
+
+install_sdk() {
+    wget https://github.com/zephyrproject-rtos/sdk-ng/releases/download/v0.16.0/zephyr-sdk-0.16.0_linux-x86_64.tar.xz && \
+         tar -xf zephyr-sdk-0.16.0_linux-x86_64.tar.xz && \
+         rm -f zephyr-sdk-0.16.0_linux-x86_64.tar.xz && \
+         cd zephyr-sdk-0.16.0/ && \
+         ./setup.sh -c -t arm-zephyr-eabi
+}
+
+install_prerequiresites
+install_sdk

.ci/docker/ubuntu/Dockerfile

@@ -84,6 +84,11 @@ RUN rm install_android.sh
 
 ARG ARM_SDK
 
+ARG ZEPHYR_SDK
+COPY ./common/install_zephyr.sh install_zephyr.sh
+RUN if [ -n "${ZEPHYR_SDK}" ]; then bash ./install_zephyr.sh; fi
+RUN rm install_zephyr.sh
+
 ARG QNN_SDK
 
 ARG MEDIATEK_SDK

.ci/scripts/build_llama_android.sh

@@ -19,7 +19,7 @@ install_executorch_and_backend_lib() {
   echo "Installing executorch and xnnpack backend"
   clean_executorch_install_folders
   mkdir cmake-android-out
-  ANDROID_NDK=/opt/ndk
+  ANDROID_NDK=${ANDROID_NDK:-/opt/ndk}
   BUCK2=buck2
   ANDROID_ABI=arm64-v8a
   cmake --preset llm \

.github/workflows/build-presets.yml

@@ -44,7 +44,7 @@ jobs:
       job-name: build
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       runner: linux.2xlarge
-      docker-image: ci-image:executorch-ubuntu-22.04-arm-sdk
+      docker-image: ci-image:executorch-ubuntu-22.04-zephyr-sdk
       submodules: recursive
       timeout: 90
       script: |

.github/workflows/docker-builds.yml

@@ -37,6 +37,7 @@ jobs:
           executorch-ubuntu-22.04-clang12,
           executorch-ubuntu-22.04-linter,
           executorch-ubuntu-22.04-arm-sdk,
+          executorch-ubuntu-22.04-zephyr-sdk,
           executorch-ubuntu-22.04-qnn-sdk,
           executorch-ubuntu-22.04-mediatek-sdk,
           executorch-ubuntu-22.04-clang12-android

.github/workflows/pull.yml

@@ -632,32 +632,33 @@ jobs:
         # run eval_llama wikitext task
         PYTHON_EXECUTABLE=python bash .ci/scripts/test_eval_llama_wikitext.sh
 
-  test-eval_llama-mmlu-linux:
-    name: test-eval_llama-mmlu-linux
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
-    permissions:
-      id-token: write
-      contents: read
-    strategy:
-      fail-fast: false
-    with:
-      runner: linux.24xlarge
-      docker-image: ci-image:executorch-ubuntu-22.04-clang12
-      submodules: 'recursive'
-      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
-      timeout: 90
-      script: |
-        # The generic Linux job chooses to use base env, not the one setup by the image
-        CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
-        conda activate "${CONDA_ENV}"
-
-        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "cmake"
-
-        # install llama requirements
-        bash examples/models/llama/install_requirements.sh
-
-        # run eval_llama mmlu task
-        PYTHON_EXECUTABLE=python bash .ci/scripts/test_eval_llama_mmlu.sh
+  # TODO(larryliu0820): Fix this issue before reenabling it: https://gist.github.com/larryliu0820/7377ecd0d79dbc06076cec8d9f2b85d2
+  # test-eval_llama-mmlu-linux:
+  #   name: test-eval_llama-mmlu-linux
+  #   uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+  #   permissions:
+  #     id-token: write
+  #     contents: read
+  #   strategy:
+  #     fail-fast: false
+  #   with:
+  #     runner: linux.24xlarge
+  #     docker-image: ci-image:executorch-ubuntu-22.04-clang12
+  #     submodules: 'recursive'
+  #     ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+  #     timeout: 90
+  #     script: |
+  #       # The generic Linux job chooses to use base env, not the one setup by the image
+  #       CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
+  #       conda activate "${CONDA_ENV}"
+
+  #       PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "cmake"
+
+  #       # install llama requirements
+  #       bash examples/models/llama/install_requirements.sh
+
+  #       # run eval_llama mmlu task
+  #       PYTHON_EXECUTABLE=python bash .ci/scripts/test_eval_llama_mmlu.sh
 
   test-llama_runner_eager-linux:
     name: test-llama_runner_eager-linux

CMakeLists.txt

@@ -161,6 +161,10 @@ endif()
 
 if(EXECUTORCH_BUILD_TESTS)
   include(CTest)
+else()
+  # It looks like some of our third-party deps will try to turn this on if it's
+  # not explicitly set, leading to confusing behavior.
+  set(BUILD_TESTING OFF)
 endif()
 
 add_subdirectory(third-party)
@@ -737,7 +741,10 @@ if(EXECUTORCH_BUILD_EXECUTOR_RUNNER)
     endif()
 
     set(CMAKE_EXECUTABLE_SUFFIX ".html")
-    target_link_options(executor_runner PUBLIC -sALLOW_MEMORY_GROWTH --embed-file "${WASM_MODEL_DIR}@/")
+    target_link_options(
+      executor_runner PUBLIC -sALLOW_MEMORY_GROWTH --embed-file
+      "${WASM_MODEL_DIR}@/"
+    )
   endif()
 endif()
 

README.md

@@ -29,6 +29,7 @@ Platform Support:
   - Arm
   - Cadence
   - MediaTek
+  - NXP
   - OpenVINO
   - Qualcomm
   - Vulkan

backends/apple/coreml/compiler/coreml_preprocess.py

@@ -28,6 +28,8 @@
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.WARNING)
 
+from executorch.backends.apple.coreml.compiler.torch_ops import *  # noqa: F401, F403
+
 
 class COMPILE_SPEC_KEYS(Enum):
     COMPUTE_UNITS = "compute_units"