XGBoost could not broadcast input array

1

I’m getting following error during tuning:

Traceback (most recent call last):
  File "/workspace/tcl_scripts/tune.py", line 152, in <module>
    main(args)
  File "/workspace/tcl_scripts/tune.py", line 99, in main
    tune_model(args, mod, params, target)
  File "/workspace/tcl_scripts/tune.py", line 74, in tune_model
    autotvm.record.load_from_file(task_log_filename))
  File "/workspace/python/tvm/autotvm/tuner/model_based_tuner.py", line 314, in load_history
    maximums = self.model_optimizer.find_maximums(base_model, self.plan_size, self.visited)
  File "/workspace/python/tvm/autotvm/tuner/sa_model_optimizer.py", line 89, in find_maximums
    scores = model.predict(points)
  File "/workspace/python/tvm/autotvm/tuner/xgboost_cost_model.py", line 295, in predict
    feas = self._get_feature(xs)
  File "/workspace/python/tvm/autotvm/tuner/xgboost_cost_model.py", line 341, in _get_feature
    ret[i, :] = t if t is not None else 0
ValueError: could not broadcast input array from shape (1219,) into shape (1021,)

Using RPC on android phone, arm64, target and target host is llvm -mtriple=aarch64-linux-gnu -device=arm_cpu