// 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).
  // Setting a larger thread pool does not help with the Swift caller, as we use
  // a different TFE context for each thread of execution (for running graph
  // functions, and their send/recvs corountines).
  config.set_inter_op_parallelism_threads(1);

      memcpy(buffer + copy_size, gcs_file->buffer.data(), remaining_copy);
      copy_size += remaining_copy;
    }
    if (copy_size < n) {
      // Forget the end-of-file flag to allow for clients that poll on the
      // same file.
      gcs_file->buffer_end_is_past_eof = false;
      TF_SetStatus(status, TF_OUT_OF_RANGE, "Read less bytes than requested");
      return copy_size;
    }