tensorflow::uint64 send_device_incarnation);

// Return a 1-D INT32 tensor containing a single value 1.
TFE_TensorHandle* TestAxisTensorHandle(TFE_Context* ctx);

// Return an op taking minimum of `input` long `axis` dimension.
TFE_Op* MinOp(TFE_Context* ctx, TFE_TensorHandle* input,
              TFE_TensorHandle* axis);

// If there is a device of type `device_type`, returns true

// Returns whether the single GPU or general XLA auto jit optimizations are
// enabled through MarkForCompilationPassFlags.
TF_CAPI_EXPORT unsigned char TF_GetXlaAutoJitEnabled();

// Sets XLA's minimum cluster size. This has global effect.
TF_CAPI_EXPORT void TF_SetXlaMinClusterSize(int size);

// Gets/Sets TF/XLA flag for whether(true) or not(false) to disable constant

    }
    lru_list_.erase(it->second.lru_iterator);
    cache_.erase(it);
    return true;
  }

  /// The maximum age of entries in the cache, in seconds. A value of 0 means
  /// that no entry is ever placed in the cache.
  const uint64_t max_age_;

  /// The maximum number of entries in the cache. A value of 0 means there is no
  /// limit on entry count.
  const size_t max_entries_;

// executed in sequence. Assigning nodes to different executors allows executing
// nodes in parallel.
// in_flight_nodes_limit: when is_async is true, this value controls the
// maximum number of in flight async nodes. Enqueuing of additional async ops
// after the limit is reached blocks until some inflight nodes finishes.
// The effect is bounding the memory held by inflight TensorHandles that are

  /// The size of the blocks stored in the LRU cache, as well as the size of the
  /// reads from the underlying filesystem.
  const size_t block_size_;
  /// The maximum number of bytes (sum of block sizes) allowed in the LRU cache.
  const size_t max_bytes_;
  /// The maximum staleness of any block in the LRU cache, in seconds.
  const uint64_t max_staleness_;
  /// The callback to read a block from the underlying filesystem.