# CUDA WHEEL
test:linux_cuda_wheel_test_filters --test_tag_filters=gpu,requires-gpu,-no_gpu,-no_oss,-tf_tosa,-oss_excluded,-oss_serial,-benchmark-test,-no_cuda11,-no_oss_py38,-no_oss_py39,-no_oss_py310,-no_oss_py313
test:linux_cuda_wheel_test_filters --build_tag_filters=gpu,requires-gpu,-no_gpu,-no_oss,-tf_tosa,-oss_excluded,-oss_serial,-benchmark-test,-no_cuda11,-no_oss_py38,-no_oss_py39,-no_oss_py310,-no_oss_py313

cuda_comment: >
   From the template it looks like you are installing **TensorFlow** (TF) prebuilt binaries:
      * For TF-GPU - See point 1
      * For TF-CPU - See point 2
   -----------------------------------------------------------------------------------------------
   
   **1. Installing **TensorFlow-GPU** (TF) prebuilt binaries**
   
   
   Make sure you are using compatible TF and CUDA versions.

[pip package](https://www.tensorflow.org/install/pip), to
[enable GPU support](https://www.tensorflow.org/install/gpu), use a
[Docker container](https://www.tensorflow.org/install/docker), and
[build from source](https://www.tensorflow.org/install/source).

To install the current release, which includes support for
[CUDA-enabled GPU cards](https://www.tensorflow.org/install/gpu) *(Ubuntu and
Windows)*:

```
$ pip install tensorflow
```

TFCI_BAZEL_TARGET_SELECTING_CONFIG_PREFIX=linux_cuda
TFCI_BUILD_PIP_PACKAGE_WHEEL_NAME_ARG="--repo_env=WHEEL_NAME=tensorflow"
TFCI_DOCKER_ARGS="--gpus all"
TFCI_LIB_SUFFIX="-gpu-linux-x86_64"
# TODO: Set back to 610M once the wheel size is fixed.

        (environ_cp.get('TF_NEED_ROCM', None) == '1')):
      test_and_build_filters += ['-no_windows_gpu', '-no_gpu']
    else:
      test_and_build_filters.append('-gpu')
  elif is_macos():
    test_and_build_filters += ['-gpu', '-nomac', '-no_mac', '-mac_excluded']
  elif is_linux():
    if ((environ_cp.get('TF_NEED_CUDA', None) == '1') or
        (environ_cp.get('TF_NEED_ROCM', None) == '1')):

        `XNNPACK` delegate automatically when the model has a `fp32` operation.
*   GPU
    *   Allow GPU acceleration starting with internal graph nodes
    *   Experimental support for quantized models with the Android GPU delegate
    *   Add GPU delegate whitelist.
    *   Rename GPU whitelist -> compatibility (list).
    *   Improve GPU compatibility list entries from crash reports.
*   NNAPI
    *   Set default value for

  // threadpool of GPU event mgr, as that can trigger more callbacks to be
  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).

# limitations under the License.
# ==============================================================================
source "${BASH_SOURCE%/*}/utilities/setup.sh"

# Record GPU count and CUDA version status
if [[ "$TFCI_NVIDIA_SMI_ENABLE" == 1 ]]; then
  tfrun nvidia-smi
fi

# Update the version numbers for Nightly only
if [[ "$TFCI_NIGHTLY_UPDATE_VERSION_ENABLE" == 1 ]]; then

  if [[ "$TFCI_PYTHON_VERSION" == "3.13" ]]; then
    "$python" -m pip install numpy==1.26.4
  else
    "$python" -m pip install numpy==1.26.0
  fi
fi
if [[ "$TFCI_BAZEL_COMMON_ARGS" =~ gpu|cuda ]]; then
  echo "Checking to make sure tensorflow[and-cuda] is installable..."
  "$python" -m pip install "$(echo *.whl)[and-cuda]" $TFCI_PYTHON_VERIFY_PIP_INSTALL_ARGS
else

        with:
          api-level: ${{ matrix.api-level }}
          arch: ${{ matrix.api-level == '34' && 'x86_64' || 'x86' }}
          force-avd-creation: false
          emulator-options: -no-window -gpu swiftshader_indirect -noaudio -no-boot-anim -camera-back none
          disable-animations: false
          script: echo "Generated AVD snapshot for caching."

      - name: Run Tests