Update 20191106-tf2-tpu-savedmodel.md

Since this API change has been approved and checked in, I now update this doc with the final accepted design and switch status to 'accepted'.

Author: lzr-official

rfcs/20191106-tf2-tpu-savedmodel.md

@@ -1,11 +1,11 @@
 # TPU SavedModel Export API for TF2.x
 
-Status        | Proposed
+Status        | Accepted
 :------------ | :-----------------------------------------------------------
 **RFC #**     | [171](https://github.com/tensorflow/community/pull/171)
 **Author(s)** | Zhuoran Liu ([email protected]), Youlong Cheng ([email protected])
 **Sponsor**   | Jonathan Hseu ([email protected])
-**Updated**   | 2019-11-06
+**Updated**   | 2020-11-06
 
 ## Objective
 
@@ -82,7 +82,61 @@ whatever reason, e.g. CPU computations can be parallelized, users don’t have
 enough TPU resources, etc. In this case, there has to be a way for them to tell
 SavedModel that only ‘dense’ is to run on TPU.</center>
 
-## Design Proposal
+## Design
+
+The general idea is to allow users to store a function-alias mapping during
+model saving, so that they can refer to the function they want to rewrite for
+TPU inference when they use downstream graph transformation tools to rewrite
+their models for TPU serving.
+
+This alias mapping mechanism is because a single tf.function can generate many
+ConcreteFunctions. If a downstream tool wants to refer to all concrete functions
+generated by a single tf.function, it can use the `function_aliases` argument to
+store a map from the alias name to all concrete function names.
+
+### Major changes
+
++   For `tf.saved_model.SaveOptions`: A new slot `function_aliases` is added, to
+    allow users specify alias of functions they potentially wish to be rewritten
+    by external graph transformation tools (TPU Inference Converter in this
+    case);
++   For `MetaInfoDef` in `MetaGraphDef` in `SavedModel`: A new field
+    `functions_aliases` is added, to store names of FunctionDef mapping to their
+    aliases.
+
+### User facing API
+
+Users can give `FunctionDef`s they potentially want to rewrite for TPU inference
+an alias when saving model:
+
+```python
+class MyModel:
+  @tf.function
+  def func():
+    ...
+  @tf.function
+  def serve():
+    ...
+    func()
+
+model = MyModel()
+signatures = {
+    'serving_default': model.serve.get_concrete_function(),
+}
+options = tf.saved_model.SaveOptions(function_aliases={
+    'my_func': model.func,
+})
+tf.saved_model.save(model, export_dir, signatures, options)
+```
+
+And leverage some model conversion tool to convert their CPU model for TPU
+serving:
+
+```python
+MyModelConversionTool(input_saved_model, output_saved_model, function_alias='my_func')
+```
+
+## Alternative Design Considered
 
 ### Caveat