update docs

Signed-off-by: Srikanth Ramakrishna <srikanth.ramakrishna@intel.com>

Author: sramakintel

pytorch/README.md

@@ -272,6 +272,13 @@ The images below are [TorchServe*] with CPU Optimizations:
 
 For more details, follow the procedure in the [TorchServe](https://github.com/pytorch/serve/blob/master/examples/intel_extension_for_pytorch/README.md) instructions.
 
+The images below are [TorchServe*] with XPU Optimizations:
+
+| Tag(s)              | Pytorch  | IPEX         | Dockerfile      |
+| ------------------- | -------- | ------------ | --------------- |
+| `2.3.110-serving-xpu` | [v2.3.1] | [v2.3.110+xpu] | [v0.4.0-Beta]   |
+
+
 ## CPU only images with Intel® Distribution for Python*
 
 The images below are built only with CPU optimizations (GPU acceleration support was deliberately excluded) and include [Intel® Distribution for Python*]:

pytorch/serving/README.md

@@ -39,7 +39,7 @@ docker run --rm -it \
            -u root \
            -v $PWD:/home/model-server \
            --device /dev/dri \
-           intel/intel-optimized-pytorch:2.1.40-serving-xpu \
+           intel/intel-optimized-pytorch:2.3.110-serving-xpu \
            sh -c 'python model-archive/ipex_squeezenet.py && \
            torch-model-archiver --model-name squeezenet1_1 \
            --version 1.1 \
@@ -73,7 +73,7 @@ docker run -d --rm --name server \
           -v $PWD/config-xpu.properties:/home/model-server/config.properties \
           --net=host \
           --device /dev/dri \
-          intel/intel-optimized-pytorch:2.1.40-serving-xpu
+          intel/intel-optimized-pytorch:2.3.110-serving-xpu
 ```
 
 After lauching the container, follow the steps below:

pytorch/serving/wf-store/rest-test.sh

@@ -33,13 +33,13 @@ apt-get -y install curl
 
 curl --fail -X GET http://localhost:8080/ping
 
-cd ../model-store || exit
+cd /home/model-server/model-store || exit
 curl --fail -O https://torchserve.pytorch.org/mar_files/cat_dog_classification.mar
 curl --fail -O https://torchserve.pytorch.org/mar_files/dog_breed_classification.mar
 curl --fail -X POST "http://127.0.0.1:8081/models?url=cat_dog_classification.mar"
 curl --fail -X POST "http://127.0.0.1:8081/models?url=dog_breed_classification.mar"
 
-cd ../wf-store || exit
+cd /home/model-server/wf-store || exit
 curl --fail -X POST "http://127.0.0.1:8081/workflows?url=dog_breed_wf.war"
 
 curl --fail -O https://raw.githubusercontent.com/pytorch/serve/master/examples/Workflows/dog_breed_classification/model_input/Cat.jpg