diff --git a/docs/readthedocs/requirements-doc.txt b/docs/readthedocs/requirements-doc.txt
index a84124df..2f383586 100644
--- a/docs/readthedocs/requirements-doc.txt
+++ b/docs/readthedocs/requirements-doc.txt
@@ -6,8 +6,8 @@ sphinxemoji
 click
 tensorflow==1.15.2
 bigdl==0.12.0
-ray[tune]==1.2.0
-ray==1.2.0
+ray[tune]==1.9.2
+ray==1.9.2
 torch==1.7.1
 Pygments==2.3.1
 setuptools==41.0.1
diff --git a/docs/readthedocs/source/doc/Orca/Overview/distributed-tuning.md b/docs/readthedocs/source/doc/Orca/Overview/distributed-tuning.md
index af28ab30..56379a2d 100644
--- a/docs/readthedocs/source/doc/Orca/Overview/distributed-tuning.md
+++ b/docs/readthedocs/source/doc/Orca/Overview/distributed-tuning.md
@@ -16,7 +16,7 @@ You can install the latest release version of BigDL Orca as follows:
 pip install --pre --upgrade bigdl-orca[automl]
 ```
 _Note that with extra key of [automl], `pip` will automatically install the additional dependencies for distributed hyper-parameter tuning,
-including `ray[tune]==1.2.0`, `scikit-learn`, `tensorboard`, `xgboost`._
+including `ray[tune]==1.9.2`, `scikit-learn`, `tensorboard`, `xgboost`._
 
 To use [Pytorch Estimator](#pytorch-autoestimator), you need to install Pytorch with `pip install torch==1.8.1`.
 
diff --git a/docs/readthedocs/source/doc/Ray/Overview/ray.md b/docs/readthedocs/source/doc/Ray/Overview/ray.md
index b4337aec..fa97a363 100644
--- a/docs/readthedocs/source/doc/Ray/Overview/ray.md
+++ b/docs/readthedocs/source/doc/Ray/Overview/ray.md
@@ -7,14 +7,14 @@ With the _**RayOnSpark**_ support packaged in [BigDL Orca](../../Orca/Overview/o
 Users can seamlessly integrate Ray applications into the big data processing pipeline on the underlying Big Data cluster 
 (such as [Hadoop/YARN](../../UserGuide/hadoop.md) or [K8s](../../UserGuide/k8s.md)).
 
-_**Note:** BigDL has been tested on Ray 1.2.0 and you are highly recommended to use this tested version._
+_**Note:** BigDL has been tested on Ray 1.9.2 and you are highly recommended to use this tested version._
 
 
 ### **1. Install**
 
 We recommend using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/) to prepare the Python environment. 
 When installing bigdl-orca with pip, you can specify the extras key `[ray]` to install the additional dependencies 
-for running Ray (i.e. `ray==1.2.0`, `psutil`, `aiohttp==3.7.0`, `aioredis==1.1.0`, `setproctitle`, `hiredis==1.1.0`, `async-timeout==3.0.1`):
+for running Ray (i.e. `ray==1.9.2`, `psutil`, `aiohttp==3.7.0`, `aioredis==1.1.0`, `setproctitle`, `hiredis==1.1.0`, `async-timeout==3.0.1`):
 
 ```bash
 conda create -n py37 python=3.7  # "py37" is conda environment name, you can use any name you like.
diff --git a/docs/readthedocs/source/doc/UserGuide/python.md b/docs/readthedocs/source/doc/UserGuide/python.md
index 62647ddf..ddbcf44e 100644
--- a/docs/readthedocs/source/doc/UserGuide/python.md
+++ b/docs/readthedocs/source/doc/UserGuide/python.md
@@ -119,7 +119,7 @@ BigDL has been tested on __Python 3.6 and 3.7__ with the following library versi
 
 ```bash
 pyspark==2.4.6 or 3.1.2
-ray==1.2.0
+ray==1.9.2
 tensorflow==1.15.0 or >2.0
 pytorch>=1.5.0
 torchvision>=0.6.0