commands above.

*Nightly binaries are available for testing using the
[tf-nightly](https://pypi.python.org/pypi/tf-nightly) and
[tf-nightly-cpu](https://pypi.python.org/pypi/tf-nightly-cpu) packages on PyPI.*

#### *Try your first TensorFlow program*

```shell
$ python
```

```python
>>> import tensorflow as tf
>>> tf.add(1, 2).numpy()
3
>>> hello = tf.constant('Hello, TensorFlow!')
>>> hello.numpy()
b'Hello, TensorFlow!'

#     monolithic:       Build all TF C++ code into a single shared object.
#     dynamic_kernels:  Try to link all kernels dynamically (experimental).
#     dbg:              Build with debug info
#
# TF version options;
#     v2: Build TF v2
#
# Feature and Third party library support options:
#     xla:          Build TF with XLA
#     tpu:          Build TF with TPU support
#     cuda:         Build with CUDA support.

typing_extensions ~= 4.14.1
gast == 0.4.0
termcolor == 2.3.0
wrapt == 1.16.0
tblib == 2.0.0
ml_dtypes >= 0.5.1, < 0.6.0
auditwheel >= 6.1.0
# Install tensorboard, and keras
# Note that here we want the latest version that matches TF major.minor version
# Note that we must use nightly here as these are used in nightly jobs
# For release jobs, we will pin these on the release branch
keras-nightly ~= 3.12.0.dev
tb-nightly ~= 2.20.0.a

typing_extensions ~= 4.14.1
gast == 0.4.0
termcolor == 2.3.0
wrapt == 1.16.0
tblib == 2.0.0
ml_dtypes >= 0.5.4, < 0.6.0
auditwheel >= 6.1.0
# Install tensorboard, and keras
# Note that here we want the latest version that matches TF major.minor version
# Note that we must use nightly here as these are used in nightly jobs
# For release jobs, we will pin these on the release branch
keras-nightly ~= 3.12.0.dev
tb-nightly ~= 2.20.0.a

    *   Added a new boolean argument `allow_fast_lookup` to `tf.nn.embedding_lookup_sparse` and `tf.nn.safe_embedding_lookup_sparse`, which enables a simplified and typically faster lookup procedure.

*   `tf.data`

    *   `tf.data.Dataset.zip` now supports Python-style zipping, i.e. `Dataset.zip(a, b, c)`.

TFCI_DOCKER_ENABLE=1
TFCI_DOCKER_IMAGE=us-docker.pkg.dev/ml-oss-artifacts-published/ml-public-container/ml-build-arm64:latest
TFCI_DOCKER_PULL_ENABLE=1
TFCI_DOCKER_REBUILD_ARGS="--target=tf ci/official/containers/ml_build_arm64"
TFCI_INDEX_HTML_ENABLE=1
TFCI_LIB_SUFFIX="-cpu-linux-arm64"
TFCI_OUTPUT_DIR=build_output
TFCI_WHL_AUDIT_ENABLE=1
TFCI_WHL_AUDIT_PLAT=manylinux_2_27_aarch64
TFCI_WHL_BAZEL_TEST_ENABLE=1

@test "bazel nobuild passes on all of TF except TF Lite and win toolchains" {
    bazel build --experimental_cc_shared_library --nobuild --keep_going -- //tensorflow/... -//tensorflow/lite/... -//tensorflow/tools/toolchains/win/... -//tensorflow/tools/toolchains/win_1803/...  -//tensorflow/tools/toolchains/win2022/...
}

@test "API compatibility test passes, ensuring no unexpected changes to the TF API" {

load("@python_version_repo//:py_version.bzl", "REQUIREMENTS")
load("@rules_python//python:pip.bzl", "compile_pip_requirements")

# TODO(ybaturina): Remove once TF is migrated to CUDA 12.9.
genrule(
    name = "nvidia_constraints",
    srcs = ["nvidia-requirements.txt"],
    outs = ["nvidia-constraints.txt"],
    cmd = """sed -E "s/>=/==/" $(location nvidia-requirements.txt) > $@;""",

)

# DO NOT ADD ANY NEW EXCEPTIONS TO THIS LIST!
# Instead, please use public APIs or public build rules TF provides.
# If you need functionality that is not exposed, we will work with you to expand our public APIs.
# TODO(b/173549186): Move Google-internal TF code out of learning/brain
package_group(
    name = "internal",
    packages = [
        "//devtools/python/indexer/...",

    else \
      echo "Nvidia packages are not installed"; \
    fi

# Setup links for TensorFlow to compile.
# Referenced in devel.usertools/*.bazelrc.
# Set python3.12 as the default python version.
# TF does not support python3.13.
RUN ln -sf /usr/bin/python3.12 /usr/bin/python3
RUN ln -sf /usr/bin/python3.12 /usr/bin/python
RUN ln -sf /usr/lib/python3.12 /usr/lib/tf_python