diff --git a/demo/dask/gpu_training.py b/demo/dask/gpu_training.py
index c6530d886..853710e31 100644
--- a/demo/dask/gpu_training.py
+++ b/demo/dask/gpu_training.py
@@ -32,6 +32,7 @@ def main(client):
 
     # you can pass output directly into `predict` too.
     prediction = xgb.dask.predict(client, bst, dtrain)
+    prediction = prediction.compute()
     print('Evaluation history:', history)
     return prediction
 
diff --git a/python-package/xgboost/core.py b/python-package/xgboost/core.py
index 6a74e0733..016344062 100644
--- a/python-package/xgboost/core.py
+++ b/python-package/xgboost/core.py
@@ -1125,7 +1125,6 @@ class Booster(object):
             _check_call(_LIB.XGBoosterLoadModelFromBuffer(handle, ptr, length))
             state['handle'] = handle
         self.__dict__.update(state)
-        self.set_param({'seed': 0})
 
     def __copy__(self):
         return self.__deepcopy__(None)
diff --git a/python-package/xgboost/dask.py b/python-package/xgboost/dask.py
index 80cb47c07..5a465412f 100644
--- a/python-package/xgboost/dask.py
+++ b/python-package/xgboost/dask.py
@@ -395,6 +395,10 @@ def train(client, params, dtrain, *args, evals=(), **kwargs):
 def predict(client, model, data, *args):
     '''Run prediction with a trained booster.
 
+      .. note::
+
+          Only default prediction mode is supported right now.
+
     Parameters
     ----------
     client: dask.distributed.Client
@@ -445,8 +449,8 @@ def predict(client, model, data, *args):
         '''Get shape of data in each worker.'''
         logging.info('Trying to get data shape on %d', worker_id)
         worker = distributed_get_worker()
-        rows, cols = data.get_worker_data_shape(worker)
-        return rows, cols
+        rows, _ = data.get_worker_data_shape(worker)
+        return rows, 1          # default is 1
 
     # Constructing a dask array from list of numpy arrays
     # See https://docs.dask.org/en/latest/array-creation.html
@@ -457,7 +461,7 @@ def predict(client, model, data, *args):
     shapes = client.gather(futures_shape)
     arrays = []
     for i in range(len(futures_shape)):
-        arrays.append(da.from_delayed(futures[i], shape=shapes[i],
+        arrays.append(da.from_delayed(futures[i], shape=(shapes[i][0], ),
                                       dtype=numpy.float32))
     predictions = da.concatenate(arrays, axis=0)
     return predictions
diff --git a/tests/python-gpu/test_gpu_with_dask.py b/tests/python-gpu/test_gpu_with_dask.py
index ce0beb119..c6a3f8407 100644
--- a/tests/python-gpu/test_gpu_with_dask.py
+++ b/tests/python-gpu/test_gpu_with_dask.py
@@ -40,3 +40,6 @@ def test_dask_dataframe(client):
 
     assert isinstance(out['booster'], dxgb.Booster)
     assert len(out['history']['X']['rmse']) == 2
+
+    predictions = dxgb.predict(out, dtrain)
+    predictions = predictions.compute()
diff --git a/tests/python/test_pickling.py b/tests/python/test_pickling.py
new file mode 100644
index 000000000..1497688d2
--- /dev/null
+++ b/tests/python/test_pickling.py
@@ -0,0 +1,48 @@
+import pickle
+import numpy as np
+import xgboost as xgb
+import os
+
+
+kRows = 100
+kCols = 10
+
+
+def generate_data():
+    X = np.random.randn(kRows, kCols)
+    y = np.random.randn(kRows)
+    return X, y
+
+
+def test_model_pickling():
+    xgb_params = {
+        'verbosity': 0,
+        'nthread': 1,
+        'tree_method': 'hist'
+    }
+
+    X, y = generate_data()
+    dtrain = xgb.DMatrix(X, y)
+    bst = xgb.train(xgb_params, dtrain)
+
+    dump_0 = bst.get_dump(dump_format='json')
+    assert dump_0
+
+    filename = 'model.pkl'
+
+    with open(filename, 'wb') as fd:
+        pickle.dump(bst, fd)
+
+    with open(filename, 'rb') as fd:
+        bst = pickle.load(fd)
+
+    with open(filename, 'wb') as fd:
+        pickle.dump(bst, fd)
+
+    with open(filename, 'rb') as fd:
+        bst = pickle.load(fd)
+
+    assert bst.get_dump(dump_format='json') == dump_0
+
+    if os.path.exists(filename):
+        os.remove(filename)
diff --git a/tests/python/test_with_dask.py b/tests/python/test_with_dask.py
index 01b8c3d3f..f2ad44080 100644
--- a/tests/python/test_with_dask.py
+++ b/tests/python/test_with_dask.py
@@ -43,14 +43,17 @@ def test_from_dask_dataframe(client):
 
     prediction = xgb.dask.predict(client, model=booster, data=dtrain)
 
+    assert prediction.ndim == 1
     assert isinstance(prediction, da.Array)
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.shape[0] == kRows
 
     with pytest.raises(ValueError):
         # evals_result is not supported in dask interface.
         xgb.dask.train(
             client, {}, dtrain, num_boost_round=2, evals_result={})
 
+    prediction = prediction.compute()  # force prediction to be computed
+
 
 def test_from_dask_array(client):
     X, y = generate_array()
@@ -59,10 +62,12 @@ def test_from_dask_array(client):
     result = xgb.dask.train(client, {}, dtrain)
 
     prediction = xgb.dask.predict(client, result, dtrain)
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.shape[0] == kRows
 
     assert isinstance(prediction, da.Array)
 
+    prediction = prediction.compute()  # force prediction to be computed
+
 
 def test_regressor(client):
     X, y = generate_array()
@@ -72,7 +77,8 @@ def test_regressor(client):
     regressor.fit(X, y, eval_set=[(X, y)])
     prediction = regressor.predict(X)
 
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.ndim == 1
+    assert prediction.shape[0] == kRows
 
     history = regressor.evals_result()
 
@@ -91,7 +97,8 @@ def test_classifier(client):
     classifier.fit(X, y,  eval_set=[(X, y)])
     prediction = classifier.predict(X)
 
-    assert prediction.shape[0] == kRows and prediction.shape[1] == kCols
+    assert prediction.ndim == 1
+    assert prediction.shape[0] == kRows
 
     history = classifier.evals_result()