Traceback (most recent call last):
  File "xla/benchmarks/experiment_runner.py", line 601, in <module>
    main()
  File "xla/benchmarks/experiment_runner.py", line 597, in main
    runner.run()
  File "xla/benchmarks/experiment_runner.py", line 65, in run
    self.run_single_experiment(experiment_config, model_config)
  File "xla/benchmarks/experiment_runner.py", line 161, in run_single_experiment
    run_metrics, output = self.timed_run(benchmark_experiment,
  File "xla/benchmarks/experiment_runner.py", line 328, in timed_run
    output = loop()
  File "xla/benchmarks/experiment_runner.py", line 310, in loop
    output = benchmark_model.model_iter_fn(
  File "xla/benchmarks/benchmark_model.py", line 154, in eval
    pred = self.module(*inputs)
  File "torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "torch/nn/parallel/distributed.py", line 1519, in forward
    inputs, kwargs = self._pre_forward(*inputs, **kwargs)
  File "torch/nn/parallel/distributed.py", line 1420, in _pre_forward
    self._sync_buffers()
  File "torch/nn/parallel/distributed.py", line 2040, in _sync_buffers
    self._sync_module_buffers(authoritative_rank)
  File "torch/nn/parallel/distributed.py", line 2044, in _sync_module_buffers
    self._default_broadcast_coalesced(authoritative_rank=authoritative_rank)
  File "torch/nn/parallel/distributed.py", line 2066, in _default_broadcast_coalesced
    self._distributed_broadcast_coalesced(bufs, bucket_size, authoritative_rank)
  File "torch/nn/parallel/distributed.py", line 1981, in _distributed_broadcast_coalesced
    dist._broadcast_coalesced(
RuntimeError: No backend type associated with device type cpu