update readme and license

Author: sgygd2004

README.md

@@ -338,6 +338,7 @@ There are two extra options: `--forward-backward-disaggregating` and `--ignore-f
 
   Enables merging forward ranks within the same TP group. After doing this, your number of ranks will be multiplied by $\frac{TP+1}{2TP}$. Be sure you are using the correct number of ranks.
 
+Currently Context Parallel and Expert parallel are not supported. `--tranformer-impl` should be `local`.
 
 # 🛠️ Security Policy
 

megatron/virtual_tensor_parallel_communication.py

@@ -1,3 +1,17 @@
+# Copyright 2025 Suanzhi Future Co., Ltd.
+#
+# 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.
+
 import torch
 import threading
 import torch.distributed as dist