build --distinct_host_configuration=false

# Store performance profiling log in the mounted artifact directory.
# The profile can be viewed by visiting chrome://tracing in a Chrome browser.
# See https://docs.bazel.build/versions/main/skylark/performance.html#performance-profiling
build --profile=/tf/pkg/profile.json.gz

# Use the rebuilt gcc toolchain to compile for manylinux2014

fi

# Note: the profile can be viewed by visiting chrome://tracing in a Chrome browser.
# See https://docs.bazel.build/versions/main/skylark/performance.html#performance-profiling

build --copt=-Wno-gnu-offsetof-extensions

# Store performance profiling log in the mounted artifact directory.
# The profile can be viewed by visiting chrome://tracing in a Chrome browser.
# See https://docs.bazel.build/versions/main/skylark/performance.html#performance-profiling
build --profile=/tf/pkg/profile.json.gz

# Use the rebuilt gcc toolchain to compile for manylinux2014

TensorFlow server (`tf.train.Server`). The TensorFlow server is intended for
internal communication only. It is not built for use in untrusted environments
or networks.

For performance reasons, the default TensorFlow server does not include any
authorization protocol and sends messages unencrypted. It accepts connections
from anywhere, and executes the graphs it is sent without performing any checks.

    id: issue-type
    attributes:
      label: Issue type
      description: What type of issue would you like to report?
      multiple: false
      options:
        - Bug
        - Build/Install
        - Performance
        - Support
        - Feature Request
        - Documentation Feature Request
        - Documentation Bug
        - Others
    validations:
      required: true
  - type: markdown
    attributes:

        replicas taking part in sync training.
    *   Performance improvements for GPU multi-worker distributed training using
        `tf.distribute.experimental.MultiWorkerMirroredStrategy`
    *   Update NVIDIA `NCCL` to `2.5.7-1` for better performance and performance
        tuning. Please see

  // When we turn on grappler, confirm that the tf.Add has been rewritten into a
  // tf.Mul.
  // This capability of checking the executed op names is currently only enabled
  // for TFRT debug build, for performance and simplicity reasons.
  if (use_tfrt) {
    TF_Buffer* buf = TF_NewBuffer();
    TFE_GetExecutedOpNames(ctx, buf, status);
    ASSERT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
#ifndef NDEBUG

  DEVICE_PLACEMENT_EXPLICIT = 0,
  // Copy the tensor to the right device but log a warning.
  DEVICE_PLACEMENT_WARN = 1,
  // Silently copy the tensor, which has a performance cost since the operation
  // will be blocked till the copy completes. This is the default policy.
  DEVICE_PLACEMENT_SILENT = 2,
  // Placement policy which silently copies int32 tensors but not other dtypes.

#include "tensorflow/core/framework/op.h"
#include "tensorflow/core/framework/op_def.pb.h"
#include "tensorflow/core/grappler/costs/graph_properties.h"
#include "tensorflow/core/grappler/costs/op_performance_data.pb.h"
#include "tensorflow/core/grappler/grappler_item.h"
#include "tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.h"
#include "tensorflow/core/platform/logging.h"

#include "tensorflow/c/c_api_macros.h"
#include "tensorflow/c/eager/c_api.h"

#ifdef __cplusplus
extern "C" {
#endif

// Resets `op_to_reset` with `op_or_function_name` and `raw_device_name`. This
// is for performance optimization by reusing an exiting unused op rather than
// creating a new op every time. If `raw_device_name` is `NULL` or empty, it
// does not set the device name. If it's not `NULL`, then it attempts to parse