tested and working

megatron/text_generation/__init__.py

+# coding=utf-8
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from .api import (
+    generate,
+    generate_and_post_process)

megatron/text_generation/communication.py

@@ -22,6 +22,7 @@ from megatron import mpu
 
 
 
+# TODO: use functions from megatron/p2p
 def recv_from_prev_pipeline_rank_(recv_buffer=None):
     """Receive from previous pipeline stage and update the
     input buffer inplace."""
@@ -38,6 +39,7 @@ def recv_from_prev_pipeline_rank_(recv_buffer=None):
 
 
 
+# TODO: use functions from megatron/p2p
 def send_to_next_pipeline_rank(tensor=None):
     """Send output to the next pipeline stage."""
     if not mpu.is_pipeline_last_stage():