try numba

src/models/esmm/model.py

 import timeit
 
+import numba
 import tensorflow as tf
 from tensorflow import feature_column as fc
 from tensorflow.python.estimator.canned import head as head_lib
@@ -94,6 +95,7 @@ def _bytes_feature(value):
     return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
 
 
+@numba.jit(nopython=True, parallel=True)
 def model_predict2(device_id, diary_ids, device_dict, diary_dict, predict_fn):
     time_1 = timeit.default_timer()
     device_info, diary_lst = device_diary_fe(device_id, diary_ids, device_dict, diary_dict)
@@ -114,13 +116,6 @@ def model_predict2(device_id, diary_ids, device_dict, diary_dict, predict_fn):
         tmp.update(device_info)
         tmp.update(diary_info)
         features = {}
-        # for (col, value) in tmp.items():
-        #     if col in int_columns:
-        #         features[col] = _int64_feature(int(value))
-        #     elif col in float_columns:
-        #         features[col] = _float_feature(float(value))
-        #     elif col in str_columns:
-        #         features[col] = _bytes_feature(str(value).encode(encoding="utf-8"))
         for col in int_columns:
             features[col] = _int64_feature(int(tmp[col]))
         for col in float_columns: