Update documentation to latest release 0.28.0.

README.md

@@ -48,20 +48,20 @@ brew services stop djl-serving
 For Ubuntu
 
 ```
-curl -O https://publish.djl.ai/djl-serving/djl-serving_0.27.0-1_all.deb
-sudo dpkg -i djl-serving_0.27.0-1_all.deb
+curl -O https://publish.djl.ai/djl-serving/djl-serving_0.28.0-1_all.deb
+sudo dpkg -i djl-serving_0.28.0-1_all.deb
 ```
 
 For Windows
 
 We are considering to create a `chocolatey` package for Windows. For the time being, you can
-download djl-serving zip file from [here](https://publish.djl.ai/djl-serving/serving-0.27.0.zip).
+download djl-serving zip file from [here](https://publish.djl.ai/djl-serving/serving-0.28.0.zip).
 
 ```
-curl -O https://publish.djl.ai/djl-serving/serving-0.27.0.zip
-unzip serving-0.27.0.zip
+curl -O https://publish.djl.ai/djl-serving/serving-0.28.0.zip
+unzip serving-0.28.0.zip
 # start djl-serving
-serving-0.27.0\bin\serving.bat
+serving-0.28.0\bin\serving.bat
 ```
 
 ### Docker

engines/python/README.md

@@ -29,13 +29,13 @@ The javadocs output is generated in the `build/doc/javadoc` folder.
 ## Installation
 You can pull the Python engine from the central Maven repository by including the following dependency:
 
-- ai.djl.python:python:0.27.0
+- ai.djl.python:python:0.28.0
 
 ```xml
 <dependency>
     <groupId>ai.djl.python</groupId>
     <artifactId>python</artifactId>
-    <version>0.27.0</version>
+    <version>0.28.0</version>
     <scope>runtime</scope>
 </dependency>
 ```

serving/docker/README.md

@@ -17,7 +17,7 @@ You can find different `compose-target` in `docker-compose.yml`, like `cpu`, `lm
 
 ## Run docker image
 
-You can find DJL latest release docker image on [dockerhub](https://hub.docker.com/r/deepjavalibrary/djl-serving/tags?page=1&name=0.27.0).
+You can find DJL latest release docker image on [dockerhub](https://hub.docker.com/r/deepjavalibrary/djl-serving/tags?page=1&name=0.28.0).
 DJLServing also publishes nightly publish to the [dockerhub nightly](https://hub.docker.com/r/deepjavalibrary/djl-serving/tags?page=1&name=nightly).
 You can just pull the image you need from there.
 
@@ -29,55 +29,55 @@ Here are a few examples to run djl-serving docker image:
 ### CPU
 
 ```shell
-docker pull deepjavalibrary/djl-serving:0.27.0
+docker pull deepjavalibrary/djl-serving:0.28.0
 
 mkdir models
 cd models
 curl -O https://resources.djl.ai/test-models/pytorch/bert_qa_jit.tar.gz
 
-docker run -it --rm -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.27.0
+docker run -it --rm -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.28.0
 ```
 
 ### GPU
 
 ```shell
-docker pull deepjavalibrary/djl-serving:0.27.0-pytorch-gpu
+docker pull deepjavalibrary/djl-serving:0.28.0-pytorch-gpu
 
 mkdir models
 cd models
 curl -O https://resources.djl.ai/test-models/pytorch/bert_qa_jit.tar.gz
 
-docker run -it --runtime=nvidia --shm-size 2g -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.27.0-pytorch-gpu
+docker run -it --runtime=nvidia --shm-size 2g -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.28.0-pytorch-gpu
 ```
 
 ### AWS Inferentia
 
 ```shell
-docker pull deepjavalibrary/djl-serving:0.27.0-pytorch-inf2
+docker pull deepjavalibrary/djl-serving:0.28.0-pytorch-inf2
 
 mkdir models
 cd models
 
 curl -O https://resources.djl.ai/test-models/pytorch/resnet18_inf2_2_4.tar.gz
-docker run --device /dev/neuron0 -it --rm -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.27.0-pytorch-inf2
+docker run --device /dev/neuron0 -it --rm -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.28.0-pytorch-inf2
 ```
 
 ### aarch64 machine
 
 ```shell
-docker pull deepjavalibrary/djl-serving:0.27.0-aarch64
+docker pull deepjavalibrary/djl-serving:0.28.0-aarch64
 
 mkdir models
 cd models
 
 curl -O https://resources.djl.ai/test-models/pytorch/resnet18_inf2_2_4.tar.gz
-docker run --device /dev/neuron0 -it --rm -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.27.0-aarch64
+docker run --device /dev/neuron0 -it --rm -v $PWD:/opt/ml/model -p 8080:8080 deepjavalibrary/djl-serving:0.28.0-aarch64
 ```
 
 ## Run docker image with custom command line arguments
 
 You can pass command line arguments to `djl-serving` directly when you using `docker run`
 
 ```
-docker run -it --rm -p 8080:8080 deepjavalibrary/djl-serving:0.27.0 djl-serving -m "djl://ai.djl.huggingface.pytorch/sentence-transformers/all-MiniLM-L6-v2"
+docker run -it --rm -p 8080:8080 deepjavalibrary/djl-serving:0.28.0 djl-serving -m "djl://ai.djl.huggingface.pytorch/sentence-transformers/all-MiniLM-L6-v2"
 ```

wlm/README.md

@@ -56,7 +56,7 @@ You can pull the server from the central Maven repository by including the follo
 <dependency>
     <groupId>ai.djl.serving</groupId>
     <artifactId>wlm</artifactId>
-    <version>0.27.0</version>
+    <version>0.28.0</version>
 </dependency>
 ```