// Causes the calling thread to block till all ops dispatched in this executor
// have been executed. Note that "execution" here refers to kernel execution /
// scheduling of copies, etc. Similar to sync execution, it doesn't guarantee
// that lower level device queues (like GPU streams) have been flushed.
//
// This call may not block for execution of ops enqueued concurrently with this
// call.

TF_CAPI_EXPORT extern void TF_ColocateWith(TF_OperationDescription* desc,
                                           TF_Operation* op);

// Call some TF_SetAttr*() function for every attr that is not
// inferred from an input and doesn't have a default value you wish to
// keep.

// `value` must point to a string of length `length` bytes.
TF_CAPI_EXPORT extern void TF_SetAttrString(TF_OperationDescription* desc,

    TF_DataType data_type, void* data, size_t len, TF_Status* status);

// Specify the server_def that enables collective ops.
// This is different to the above function in that it doesn't create remote
// contexts, and remotely executing ops is not possible. It just enables
// communication for collective ops.
TF_CAPI_EXPORT extern void TFE_EnableCollectiveOps(TFE_Context* ctx,