diff --git a/paddle/fluid/inference/analysis/README.md b/paddle/fluid/inference/analysis/README.md
index 70adb4a974cc5f9911cb302840bbef7ec2591505..9a53ce53ab6a756af666de99c8729bf3da2e4a09 100644
--- a/paddle/fluid/inference/analysis/README.md
+++ b/paddle/fluid/inference/analysis/README.md
@@ -6,13 +6,13 @@ and make the various optimization features be pluggable and co-exist in a pipeli
 
 We borrowed some concepts from LLVM, such as
 
-- [Pass](./pass.h)es to implement optimization that traverse the inference program,
-- [DataFlowGraph](./data_flow_graph.h) to represent the data flow graph built from a program,
-- [PassManager](./pass_manager.h) to manage a sequence of `Pass`es over a graph.
+- [Pass](../../framework/ir/pass.h)es to implement optimization that traverse the inference program,
+- [Graph](../../framework/ir/graph.h) to represent the data flow graph built from a program,
+- [PassManager](./ir_pass_manager.h) to manage a sequence of `Pass`es over a graph.
 
 There are some other basic concepts here
 
-- [Node](./node.h), the node in a `DataFlowGraph`,
+- [Node](../../framework/ir/node.h), the node in a `Graph`,
   - `Function`, the Operator in Fluid,
   - `Value`, the Variable in Fluid;
 - [Argument](./argument.h), the argument that treat as the input and output of all `Pass`es in the pipeline,
@@ -21,9 +21,9 @@ There are some other basic concepts here
 
 The `inference/analysis` module make all the passes in a pipeline, and works in such way:
 
-1. Build a `DataFlowGraph` from a Fluid inference ProgramDesc,
-2. Call the middle passes one by one, the same `DataFlowGraph` is passed across all the passes,
-3. Transform a new ProgramDesc from the modified `DataFlowGraph`.
+1. Build a `Graph` from a Fluid inference ProgramDesc,
+2. Call the middle passes one by one, the same `Graph` is passed across all the passes,
+3. Transform a new ProgramDesc from the modified `Graph`.
 
 The new optimization features can be added as an independent `Pass` and controlled by gflags,
 each pass will generate unified debug information or visualization for better debugging.
@@ -54,5 +54,5 @@ It can be used as a helper class that draws the modified graph after each pass.
 There is some helper legacy/function/class for analysis.
 
 - [dot.h](./dot.h) give a easy to use interface for generating `DOT` codes,
-- [graph_traits.h](./graph_traits.h) contains the interfaces of the graph traversal algorithms, it uses `iterator`to make the algorithms easy to share across different passes,
-there are some implementations in  [data_flow_graph.cc](./data_flow_graph.cc) , such as BFS and DFS..
+- [graph_traits.h](../../framework/ir/graph_traits.h) contains the interfaces of the graph traversal algorithms, it uses `iterator`to make the algorithms easy to share across different passes,
+there are some implementations in  [graph_helper.cc](../../framework/ir/graph_helper.cc) , such as BFS and DFS..
diff --git a/paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md b/paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md
index 1fc35f86bcbc5b595f43569f14e1d2e2bc63c3ad..51870e804144a002b15750ee8c8fa9f4c0af40dc 100644
--- a/paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md
+++ b/paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md
@@ -18,7 +18,7 @@ For reference, please examine the code of unit test enclosed in [analyzer_int8_i
 
 * ### Create Analysis config
 
-INT8 quantization is one of the optimizations in analysis config. More information about analysis config can be found [here](https://github.com/PaddlePaddle/FluidDoc/blob/develop/doc/fluid/advanced_usage/deploy/inference/native_infer_en.md#upgrade-performance-based-on-contribanalysisconfig-prerelease)
+INT8 quantization is one of the optimizations in analysis config. More information about analysis config can be found [here](https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/native_infer_en.html#a-name-use-analysisconfig-to-manage-inference-configurations-use-analysisconfig-to-manage-inference-configurations-a)
 
 * ### Create quantize config by analysis config