# check This script checks for such errors early
if ! grep "rbe_$TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX" .bazelrc; then
  cat <<EOF
ERROR: RBE was enabled via the 'rbe' env in the 'TFCI' variable.
       TFCI: $TFCI
       TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX is "$TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX".
       But in .bazelrc, there is no "rbe_$TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX".

# ==============================================================================
source ci/official/envs/linux_x86
TFCI_BAZEL_COMMON_ARGS="--repo_env=TF_PYTHON_VERSION=$TFCI_PYTHON_VERSION --config release_gpu_linux"
TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX=linux_cuda
TFCI_BUILD_PIP_PACKAGE_ARGS="--repo_env=WHEEL_NAME=tensorflow"
TFCI_DOCKER_ARGS="--gpus all"
TFCI_LIB_SUFFIX="-gpu-linux-x86_64"

# > TF's gen_api_init_files has a genrule to run the core TensorFlow code
# > on the host machine. If we don't have --distinct_host_configuration=false,
# > the core TensorFlow code will be built once for the host and once for the
# > target platform.
# See also https://docs.bazel.build/versions/master/guide.html#build-configurations-and-cross-compilation
build --distinct_host_configuration=false

# Store performance profiling log in the mounted artifact directory.

specific Python version.

##### Parameters
`path_to_tensorflow_wheel`: The local path to the TensorFlow wheel file.
Example: `/tmp/tensorflow-2.14.0-cp311-cp311-linux_x86_64.whl`

`python_version`: The target Python version, replacing `.` with `_`.
Example: For Python 3.11, use `3_11`

The script performs the following steps:

1. Navigates to the `../requirements_updater` directory.

# ==============================================================================
source ci/official/envs/macos_x86
TFCI_BAZEL_COMMON_ARGS="--repo_env=TF_PYTHON_VERSION=$TFCI_PYTHON_VERSION  --config cross_compile_macos_x86"
TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX=cross_compile_macos_x86
TFCI_MACOS_CROSS_COMPILE_ENABLE=1
TFCI_MACOS_CROSS_COMPILE_SDK_DEST="tensorflow/tools/toolchains/cross_compile/cc/MacOSX.sdk"

    hdrs = [":includes"],
    strip_include_prefix="site-packages/numpy/core/include/",
)
""",
    ),
}

pip_parse(
    name = "pypi",
    annotations = NUMPY_ANNOTATIONS,
    python_interpreter_target = interpreter,
    requirements = "//:requirements_lock_" + TF_PYTHON_VERSION.replace(".", "_") + ".txt",
)

load("@pypi//:requirements.bzl", "install_deps")

install_deps()

#   "build_file" item that indicates the script used.
ci/official/wheel.sh

# Advanced: Select specific build/test targets with "any.sh".
# TF_ANY_TARGETS=":your/target" TF_ANY_MODE="test" ci/official/any.sh

# Afterwards: Examine the results, which will include: The bazel cache,
# generated artifacts like .whl files, and "script.log", from the script.

# limitations under the License.
# ==============================================================================
TFCI_BAZEL_COMMON_ARGS="--repo_env=TF_PYTHON_VERSION=$TFCI_PYTHON_VERSION --config release_arm64_linux"
TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX=linux_arm64
# Note: this is not set to "--cpu", because that changes the package name
# to tensorflow_cpu. These ARM builds are supposed to have the name "tensorflow"
# despite lacking Nvidia CUDA support.

ways to detect malicious models/graphs/checkpoints, so the recommended way to
mitigate the risk in this scenario is to sandbox the model execution.

### Hardware attacks

Physical GPUs or TPUs can also be the target of attacks. [Published
research](https://scholar.google.com/scholar?q=gpu+side+channel) shows that it
might be possible to use side channel attacks on the GPU to leak data from other

source ci/official/envs/linux_arm64
TFCI_BAZEL_COMMON_ARGS="--repo_env=TF_PYTHON_VERSION=$TFCI_PYTHON_VERSION --config  cross_compile_linux_arm64"