)

load(
    "@rules_ml_toolchain//gpu/cuda:cuda_configure.bzl",
    "cuda_configure",
)

cuda_configure(name = "local_config_cuda")

load(
    "@rules_ml_toolchain//gpu/nccl:nccl_redist_init_repository.bzl",
    "nccl_redist_init_repository",
)

nccl_redist_init_repository()

load(
    "@rules_ml_toolchain//gpu/nccl:nccl_configure.bzl",
    "nccl_configure",
)

# 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_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_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
```

    and
    [GPU developer Dockerfile](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tools/dockerfiles/dockerfiles/devel-gpu.Dockerfile)
    for the required packages. Alternatively, use the said
    [tensorflow/build Docker images](https://hub.docker.com/r/tensorflow/build)
    (`tensorflow/tensorflow:devel` and `tensorflow/tensorflow:devel-gpu` are no

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.

  TFE_Op* matmul = MatMulOp(ctx, m, m);

  // Disable the test if no GPU is present.
  string gpu_device_name;
  if (GetDeviceName(ctx, &gpu_device_name, "GPU")) {
    TFE_OpSetDevice(matmul, "GPU:0", status);
    ASSERT_TRUE(TF_GetCode(status) == TF_OK) << TF_Message(status);
    const char* device_name = TFE_OpGetDevice(matmul, status);
    ASSERT_TRUE(strstr(device_name, "GPU:0") != nullptr);

    TFE_OpSetDevice(matmul, "CPU:0", status);

        (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')):

  switch (ctx.device_type) {
    case DLDeviceType::kDLCPU:
      return "CPU:0";
    case DLDeviceType::kDLCUDA:
      return absl::StrCat("GPU:", ctx.device_id);
    case DLDeviceType::kDLROCM:
      return absl::StrCat("GPU:", ctx.device_id);
    default:
      return absl::nullopt;
  }
}

// Converts DLPack data type to TF_DATATYPE.

        `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