// Grad for Softmax Input
    TF_RETURN_IF_ERROR(BroadcastMul(
        ctx, grad_outputs[0], forward_outputs_[1],
        grad_inputs.subspan(0, 1)));  // upstream_grad * local softmax grad

    // Grad for labels is null
    grad_inputs[1] = nullptr;
    return absl::OkStatus();
  }
  ~SparseSoftmaxCrossEntropyWithLogitsGradientFunction() override {}

 private:
  vector<AbstractTensorHandle*> forward_outputs_;
};

#include "tensorflow/c/eager/tfe_monitoring_reader_internal.h"

template <typename... LabelType>
int64_t TFE_MonitoringCounterReader::Read(const LabelType&... labels) {
  return counter->Read(labels...);
}

TFE_MonitoringCounterReader* TFE_MonitoringNewCounterReader(const char* name) {
  auto* result = new TFE_MonitoringCounterReader(name);

  return result;
}

}

TEST(RamFileBlockCacheTest, ParallelReads) {
  // This fetcher won't respond until either `callers` threads are calling it
  // concurrently (at which point it will respond with success to all callers),
  // or 10 seconds have elapsed (at which point it will respond with an error).
  const int callers = 4;
  BlockingCounter counter(callers);
  auto fetcher = [&counter](const string& filename, size_t offset, size_t n,