required: true

-   type: textarea id: code-to-reproduce attributes: label: Standalone code to
    reproduce the issue description: Provide a reproducible test case that is
    the bare minimum necessary to generate the problem. If possible, please
    share a link to Colab/Jupyter/any notebook. placeholder: Tell us what you
    see! value: render: shell validations: required: true

- TensorFlow version (or github SHA if from source):


**Provide the text output from tflite_convert**

```
# Copy and paste here
```

**Standalone code to reproduce the issue** 
Provide a reproducible test case that is the bare minimum necessary to generate
the problem. If possible, please share a link to Colab/Jupyter/any notebook.

Also, please include a link to a GraphDef or the model if possible.

**Any other info / logs**

TFCI_MACOS_TWINE_INSTALL_ENABLE=1
TFCI_OUTPUT_DIR=build_output
TFCI_WHL_BAZEL_TEST_ENABLE=1
TFCI_WHL_SIZE_LIMIT=255M
TFCI_WHL_SIZE_LIMIT_ENABLE=1

# 3.11 is the system python on our images
case $TFCI_PYTHON_VERSION in
3.11)
  TFCI_MACOS_PYENV_INSTALL_ENABLE=0
  TFCI_MACOS_UPGRADE_PYENV_ENABLE=0
  ;;
*)
  TFCI_MACOS_PYENV_INSTALL_ENABLE=1
  TFCI_MACOS_UPGRADE_PYENV_ENABLE=1
  ;;

        # If the branch is not present, then diff against origin/master
        git diff --diff-filter ACMRT --name-only origin/master > $BATS_FILE_TMPDIR/changed_files
    fi
}

# Note: this is excluded on the full code base, since any submitted code must
# have passed Google's internal style guidelines.
@test "Check buildifier formatting on BUILD files" {
    echo "buildifier formatting is recommended. Here are the suggested fixes:"

        # If the branch is not present, then diff against origin/master
        git diff --diff-filter ACMRT --name-only origin/master > $BATS_FILE_TMPDIR/changed_files
    fi
}

# Note: this is excluded on the full code base, since any submitted code must
# have passed Google's internal style guidelines.
@test "Check buildifier formatting on BUILD files" {
    echo "buildifier formatting is recommended. Here are the suggested fixes:"

TFCI_MACOS_BAZEL_TEST_DIR_PATH="/Volumes/BuildData/bazel_output"
TFCI_OUTPUT_DIR=build_output
TFCI_WHL_BAZEL_TEST_ENABLE=1
TFCI_WHL_SIZE_LIMIT=240M
TFCI_WHL_SIZE_LIMIT_ENABLE=1

# 3.11 is the system python on our images
case $TFCI_PYTHON_VERSION in
3.11)
  TFCI_MACOS_PYENV_INSTALL_ENABLE=0
  ;;
*)
  TFCI_MACOS_PYENV_INSTALL_ENABLE=1
  ;;

}

@test "Wheel conforms to upstream size limitations" {
    WHEEL_MEGABYTES=$(stat --format %s "$TF_WHEEL" | awk '{print int($1/(1024*1024))}')
    # Googlers: search for "test_tf_whl_size"
    case "$TF_WHEEL" in
        # CPU:
        *cpu*manylinux*) LARGEST_OK_SIZE=220 ;;
        # GPU:
        *manylinux*)     LARGEST_OK_SIZE=580 ;;
        # Unknown:
        *)

- Google Play Services version
  (`Settings` > `Apps` > `Google Play Services` > `App details`):

**Standalone code to reproduce the issue**
Provide a reproducible test case that is the bare minimum necessary to generate
the problem. If possible, please share a link to or attach code demonstrating
the problem.

**Any other info / logs**

executed.

The security impact of skipping those checks should be low, since the attack
scenario would require a malicious user to be able to control the model which as
stated above is already equivalent to code execution. In any case, the
recommendation is not to serve models using Eager mode since it also has
performance limitations.

## Multi-Tenant environments

It is possible to run multiple TensorFlow models in parallel. For example,

-   We can't move forward if these tests fail.
-   In such situations, we may request you to make further changes to your PR
    for the tests to pass.
-   Once the tests pass, we now bring all the code into the internal code base,
    using a job called "copybara".

**5. Copy to Google Internal codebase and run internal CI**

-   Once the PR is in the Google codebase, we make sure it integrates well with