AttributeError: 'XGBoostCostModel' object has no attribute 'pool'

[y00423502]

When execute cmd python -m tvm.driver.tvmc tune
--target "llvm"
--output resnet50-v2-7-autotuner_records.json
resnet50-v2-7.onnx:
Traceback (most recent call last):
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/local/mnt2/workspace/learn/tvm/python/tvm/driver/tvmc/main.py", line 24, in
tvmc.main.main()
File "/local/mnt2/workspace/learn/tvm/python/tvm/driver/tvmc/main.py", line 115, in main
sys.exit(_main(sys.argv[1:]))
File "/local/mnt2/workspace/learn/tvm/python/tvm/driver/tvmc/main.py", line 103, in _main
return args.func(args)
File "/local/mnt2/workspace/learn/tvm/python/tvm/driver/tvmc/autotuner.py", line 295, in drive_tune
additional_target_options=reconstruct_target_args(args),
File "/local/mnt2/workspace/learn/tvm/python/tvm/driver/tvmc/autotuner.py", line 493, in tune_model
tune_tasks(tasks, tuning_records, **tuning_options)
File "/local/mnt2/workspace/learn/tvm/python/tvm/driver/tvmc/autotuner.py", line 675, in tune_tasks
tuner_obj = XGBTuner(tsk, loss_type="rank")
File "/local/mnt2/workspace/learn/tvm/python/tvm/autotvm/tuner/xgboost_tuner.py", line 91, in init
log_interval=log_interval // 2,
File "/local/mnt2/workspace/learn/tvm/python/tvm/autotvm/tuner/xgboost_cost_model.py", line 79, in init
xgb = import("xgboost")
File "/local/mnt2/workspace/software/pypack/xgboost/init.py", line 11, in
from .core import DMatrix, DeviceQuantileDMatrix, Booster
File "/local/mnt2/workspace/software/pypack/xgboost/core.py", line 20, in
from .compat import (
File "/local/mnt2/workspace/software/pypack/xgboost/compat.py", line 202, in
import sparse
File "/local/mnt2/workspace/learn/tvm/python/tvm/topi/sparse/init.py", line 22, in
from .csrmv import csrmv
File "/local/mnt2/workspace/learn/tvm/python/tvm/topi/sparse/csrmv.py", line 21, in
from .. import tag
ValueError: attempted relative import beyond top-level package
Exception ignored in: <bound method XGBoostCostModel.del of <tvm.autotvm.tuner.xgboost_cost_model.XGBoostCostModel object at 0x7fa0cc7a0048>>
Traceback (most recent call last):
File "/local/mnt2/workspace/learn/tvm/python/tvm/autotvm/tuner/xgboost_cost_model.py", line 354, in del
self._close_pool()
File "/local/mnt2/workspace/learn/tvm/python/tvm/autotvm/tuner/xgboost_cost_model.py", line 163, in _close_pool
if self.pool:
AttributeError: 'XGBoostCostModel' object has no attribute 'pool'

My python and xgboost version is here:python 3.6.9 xgboost 1.1.0