From 1034ff9bce2937e9c4d3d2835c4294490669493c Mon Sep 17 00:00:00 2001
From: liu-shaojun <johnssalyn@outlook.com>
Date: Fri, 23 Aug 2024 02:08:09 +0000
Subject: [PATCH] update docker image tag to 2.2.0-SNAPSHOT

---
 .github/workflows/manually_build.yml          |  8 ++---
 docker/llm/README.md                          | 16 ++++-----
 docker/llm/README_backup.md                   | 34 +++++++++----------
 docker/llm/finetune/lora/cpu/docker/README.md |  6 ++--
 .../finetune/lora/cpu/kubernetes/values.yaml  |  2 +-
 .../finetune/qlora/cpu/kubernetes/values.yaml |  2 +-
 docker/llm/finetune/xpu/README.md             |  8 ++---
 docker/llm/inference/cpu/docker/README.md     |  6 ++--
 docker/llm/inference/xpu/docker/README.md     |  4 +--
 docker/llm/serving/cpu/docker/Dockerfile      |  2 +-
 docker/llm/serving/cpu/docker/README.md       |  4 +--
 docker/llm/serving/cpu/kubernetes/README.md   |  6 ++--
 .../serving/cpu/kubernetes/deployment.yaml    |  4 +--
 docker/llm/serving/xpu/docker/Dockerfile      |  2 +-
 docker/llm/serving/xpu/docker/README.md       |  4 +--
 15 files changed, 54 insertions(+), 54 deletions(-)

diff --git a/.github/workflows/manually_build.yml b/.github/workflows/manually_build.yml
index bc84d9f094e..dd4d4d7b04d 100644
--- a/.github/workflows/manually_build.yml
+++ b/.github/workflows/manually_build.yml
@@ -24,9 +24,9 @@ on:
   #       - ipex-llm-finetune-qlora-cpu-k8s
   #       - ipex-llm-finetune-xpu
   #     tag:
-  #       description: 'docker image tag (e.g. 2.1.0-SNAPSHOT)'
+  #       description: 'docker image tag (e.g. 2.2.0-SNAPSHOT)'
   #       required: true
-  #       default: '2.1.0-SNAPSHOT'
+  #       default: '2.2.0-SNAPSHOT'
   #       type: string
   workflow_call:
     inputs:
@@ -40,9 +40,9 @@ on:
         default: 'all'
         type: string
       tag:
-        description: 'docker image tag (e.g. 2.1.0-SNAPSHOT)'
+        description: 'docker image tag (e.g. 2.2.0-SNAPSHOT)'
         required: true
-        default: '2.1.0-SNAPSHOT'
+        default: '2.2.0-SNAPSHOT'
         type: string
       public:
         description: "if the docker image push to public docker hub"
diff --git a/docker/llm/README.md b/docker/llm/README.md
index 2af11953439..b50718ff1fd 100644
--- a/docker/llm/README.md
+++ b/docker/llm/README.md
@@ -13,20 +13,20 @@ You can run IPEX-LLM containers (via docker or k8s) for inference, serving and f
 #### Pull a IPEX-LLM Docker Image
 To pull IPEX-LLM Docker images from [Docker Hub](https://hub.docker.com/u/intelanalytics), use the `docker pull` command. For instance, to pull the CPU inference image:
 ```bash
-docker pull intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT
 ```
 
 Available images in hub are: 
 
 | Image Name | Description |
 | --- | --- |
-| intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT | CPU Inference |
-| intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT | GPU Inference |
-| intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT | CPU Serving|
-| intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT | GPU Serving|
-| intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.1.0-SNAPSHOT | CPU Finetuning via Docker|
-| intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.1.0-SNAPSHOT|CPU Finetuning via Kubernetes|
-| intelanalytics/ipex-llm-finetune-qlora-xpu:2.1.0-SNAPSHOT| GPU Finetuning|
+| intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT | CPU Inference |
+| intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT | GPU Inference |
+| intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT | CPU Serving|
+| intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT | GPU Serving|
+| intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.2.0-SNAPSHOT | CPU Finetuning via Docker|
+| intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.2.0-SNAPSHOT|CPU Finetuning via Kubernetes|
+| intelanalytics/ipex-llm-finetune-qlora-xpu:2.2.0-SNAPSHOT| GPU Finetuning|
 
 #### Run a Container
 Use `docker run` command to run an IPEX-LLM docker container. For detailed instructions, refer to the [IPEX-LLM Docker Container Guides](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/DockerGuides/index.html).
diff --git a/docker/llm/README_backup.md b/docker/llm/README_backup.md
index 409461080ed..2b8e73afe8b 100644
--- a/docker/llm/README_backup.md
+++ b/docker/llm/README_backup.md
@@ -30,14 +30,14 @@ This guide provides step-by-step instructions for installing and using IPEX-LLM
 
 Run the following command to pull image:
 ```bash
-docker pull intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT
 ```
 
 ### 2. Start bigdl-llm-cpu Docker Container
 
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT
 export CONTAINER_NAME=my_container
 export MODEL_PATH=/llm/models[change to your model path]
 
@@ -156,7 +156,7 @@ Additionally, for examples related to Inference with Speculative Decoding, you c
 
 Run the following command to pull image from dockerhub:
 ```bash
-docker pull intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
 ```
 
 ### 2. Start Chat Inference
@@ -167,7 +167,7 @@ To map the xpu into the container, you need to specify --device=/dev/dri when bo
 
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
 export CONTAINER_NAME=my_container
 export MODEL_PATH=/llm/models[change to your model path]
 
@@ -189,7 +189,7 @@ Execute a quick performance benchmark by starting the ipex-llm-xpu container, sp
 To map the XPU into the container, specify `--device=/dev/dri` when booting the container.
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
 export CONTAINER_NAME=my_container
 export MODEL_PATH=/llm/models [change to your model path]
 
@@ -226,7 +226,7 @@ IPEX-LLM is integrated into FastChat so that user can use IPEX-LLM as a serving
 Run the following command:
 
 ```bash
-docker pull intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
 ```
 
 ### 2. Start ipex-llm-serving-cpu Docker Container
@@ -234,7 +234,7 @@ docker pull intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
 Please be noted that the CPU config is specified for Xeon CPUs, change it accordingly if you are not using a Xeon CPU.
 
 ```bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
 export CONTAINER_NAME=my_container
 export MODEL_PATH=/llm/models[change to your model path]
 
@@ -349,7 +349,7 @@ IPEX-LLM is integrated into FastChat so that user can use IPEX-LLM as a serving
 Run the following command:
 
 ```bash
-docker pull intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT
 ```
 
 ### 2. Start ipex-llm-serving-xpu Docker Container
@@ -357,7 +357,7 @@ docker pull intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT
 To map the `xpu` into the container, you need to specify `--device=/dev/dri` when booting the container.
 
 ```bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT
 export CONTAINER_NAME=my_container
 export MODEL_PATH=/llm/models[change to your model path]
 
@@ -473,10 +473,10 @@ You can download directly from Dockerhub like:
 
 ```bash
 # For standalone
-docker pull intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.2.0-SNAPSHOT
 
 # For k8s
-docker pull intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.2.0-SNAPSHOT
 ```
 
 Or build the image from source:
@@ -489,7 +489,7 @@ export HTTPS_PROXY=your_https_proxy
 docker build \
   --build-arg http_proxy=${HTTP_PROXY} \
   --build-arg https_proxy=${HTTPS_PROXY} \
-  -t intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.1.0-SNAPSHOT \
+  -t intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.2.0-SNAPSHOT \
   -f ./Dockerfile .
 
 # For k8s
@@ -499,7 +499,7 @@ export HTTPS_PROXY=your_https_proxy
 docker build \
   --build-arg http_proxy=${HTTP_PROXY} \
   --build-arg https_proxy=${HTTPS_PROXY} \
-  -t intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.1.0-SNAPSHOT \
+  -t intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.2.0-SNAPSHOT \
   -f ./Dockerfile.k8s .
 ```
 
@@ -520,7 +520,7 @@ docker run -itd \
    -e https_proxy=${HTTPS_PROXY} \
    -v $BASE_MODE_PATH:/ipex_llm/model \
    -v $DATA_PATH:/ipex_llm/data/alpaca-cleaned \
-   intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.1.0-SNAPSHOT
+   intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.2.0-SNAPSHOT
 ```
 
 The download and mount of base model and data to a docker container demonstrates a standard fine-tuning process. You can skip this step for a quick start, and in this way, the fine-tuning codes will automatically download the needed files:
@@ -534,7 +534,7 @@ docker run -itd \
    --name=ipex-llm-fintune-qlora-cpu \
    -e http_proxy=${HTTP_PROXY} \
    -e https_proxy=${HTTPS_PROXY} \
-   intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.1.0-SNAPSHOT
+   intelanalytics/ipex-llm-finetune-qlora-cpu-standalone:2.2.0-SNAPSHOT
 ```
 
 However, we do recommend you to handle them manually, because the automatical download can be blocked by Internet access and Huggingface authentication etc. according to different environment, and the manual method allows you to fine-tune in a custom way (with different base model and dataset).
@@ -593,7 +593,7 @@ The following shows how to fine-tune LLM with Quantization (QLoRA built on IPEX-
 Run the following command:
 
 ```bash
-docker pull intelanalytics/ipex-llm-finetune-xpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-finetune-xpu:2.2.0-SNAPSHOT
 ```
 
 ### 2. Prepare Base Model, Data and Start Docker Container
@@ -606,7 +606,7 @@ export DATA_PATH=your_downloaded_data_path
 export HTTP_PROXY=your_http_proxy
 export HTTPS_PROXY=your_https_proxy
 export CONTAINER_NAME=my_container
-export DOCKER_IMAGE=intelanalytics/ipex-llm-finetune-xpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-finetune-xpu:2.2.0-SNAPSHOT
 
 docker run -itd \
    --net=host \
diff --git a/docker/llm/finetune/lora/cpu/docker/README.md b/docker/llm/finetune/lora/cpu/docker/README.md
index de5df38fa44..4dd78ebec84 100644
--- a/docker/llm/finetune/lora/cpu/docker/README.md
+++ b/docker/llm/finetune/lora/cpu/docker/README.md
@@ -5,7 +5,7 @@
 You can download directly from Dockerhub like:
 
 ```bash
-docker pull intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-finetune-lora-cpu:2.2.0-SNAPSHOT
 ```
 
 Or build the image from source:
@@ -17,7 +17,7 @@ export HTTPS_PROXY=your_https_proxy
 docker build \
   --build-arg http_proxy=${HTTP_PROXY} \
   --build-arg https_proxy=${HTTPS_PROXY} \
-  -t intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT \
+  -t intelanalytics/ipex-llm-finetune-lora-cpu:2.2.0-SNAPSHOT \
   -f ./Dockerfile .
 ```
 
@@ -33,7 +33,7 @@ docker run -itd \
  -e WORKER_COUNT_DOCKER=your_worker_count \
  -v your_downloaded_base_model_path:/ipex_llm/model \
  -v your_downloaded_data_path:/ipex_llm/data/alpaca_data_cleaned_archive.json \
- intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT \
+ intelanalytics/ipex-llm-finetune-lora-cpu:2.2.0-SNAPSHOT \
  bash
 ```
 
diff --git a/docker/llm/finetune/lora/cpu/kubernetes/values.yaml b/docker/llm/finetune/lora/cpu/kubernetes/values.yaml
index aebfd76792b..4555bfa383e 100644
--- a/docker/llm/finetune/lora/cpu/kubernetes/values.yaml
+++ b/docker/llm/finetune/lora/cpu/kubernetes/values.yaml
@@ -1,4 +1,4 @@
-imageName: intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT
+imageName: intelanalytics/ipex-llm-finetune-lora-cpu:2.2.0-SNAPSHOT
 trainerNum: 8
 microBatchSize: 8
 nfsServerIp: your_nfs_server_ip
diff --git a/docker/llm/finetune/qlora/cpu/kubernetes/values.yaml b/docker/llm/finetune/qlora/cpu/kubernetes/values.yaml
index ccb85047960..89087c6efe3 100644
--- a/docker/llm/finetune/qlora/cpu/kubernetes/values.yaml
+++ b/docker/llm/finetune/qlora/cpu/kubernetes/values.yaml
@@ -1,4 +1,4 @@
-imageName: intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.1.0-SNAPSHOT
+imageName: intelanalytics/ipex-llm-finetune-qlora-cpu-k8s:2.2.0-SNAPSHOT
 trainerNum: 2
 microBatchSize: 8
 enableGradientCheckpoint: false # true will save more memory but increase latency
diff --git a/docker/llm/finetune/xpu/README.md b/docker/llm/finetune/xpu/README.md
index d9579d0825e..d21c6e655d8 100644
--- a/docker/llm/finetune/xpu/README.md
+++ b/docker/llm/finetune/xpu/README.md
@@ -19,7 +19,7 @@ With this docker image, we can use all [ipex-llm finetune examples on Intel GPU]
 You can download directly from Dockerhub like:
 
 ```bash
-docker pull intelanalytics/ipex-llm-finetune-xpu:2.1.0-SNAPSHOT
+docker pull intelanalytics/ipex-llm-finetune-xpu:2.2.0-SNAPSHOT
 ```
 
 Or build the image from source:
@@ -31,7 +31,7 @@ export HTTPS_PROXY=your_https_proxy
 docker build \
   --build-arg http_proxy=${HTTP_PROXY} \
   --build-arg https_proxy=${HTTPS_PROXY} \
-  -t intelanalytics/ipex-llm-finetune-xpu:2.1.0-SNAPSHOT \
+  -t intelanalytics/ipex-llm-finetune-xpu:2.2.0-SNAPSHOT \
   -f ./Dockerfile .
 ```
 
@@ -55,7 +55,7 @@ docker run -itd \
    -v $BASE_MODE_PATH:/model \
    -v $DATA_PATH:/data/alpaca-cleaned \
    --shm-size="16g" \
-   intelanalytics/ipex-llm-finetune-xpu:2.1.0-SNAPSHOT
+   intelanalytics/ipex-llm-finetune-xpu:2.2.0-SNAPSHOT
 ```
 
 The download and mount of base model and data to a docker container demonstrates a standard fine-tuning process. You can skip this step for a quick start, and in this way, the fine-tuning codes will automatically download the needed files:
@@ -72,7 +72,7 @@ docker run -itd \
    -e http_proxy=${HTTP_PROXY} \
    -e https_proxy=${HTTPS_PROXY} \
    --shm-size="16g" \
-   intelanalytics/ipex-llm-finetune-xpu:2.1.0-SNAPSHOT
+   intelanalytics/ipex-llm-finetune-xpu:2.2.0-SNAPSHOT
 ```
 
 However, we do recommend you to handle them manually, because the download can be blocked by Internet access and Huggingface authentication etc. according to different environment, and the manual method allows you to fine-tune in a custom way (with different base model and dataset).
diff --git a/docker/llm/inference/cpu/docker/README.md b/docker/llm/inference/cpu/docker/README.md
index c8babfacac0..a0f80bdcf9b 100644
--- a/docker/llm/inference/cpu/docker/README.md
+++ b/docker/llm/inference/cpu/docker/README.md
@@ -6,7 +6,7 @@ docker build \
   --build-arg http_proxy=.. \
   --build-arg https_proxy=.. \
   --build-arg no_proxy=.. \
-  --rm --no-cache -t intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT .
+  --rm --no-cache -t intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT .
 ```
 
 
@@ -16,7 +16,7 @@ docker build \
 An example could be:
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \
@@ -41,7 +41,7 @@ You can download models and bind the model directory from host machine to contai
 
 Here is an example:
 ```bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT
 export MODEL_PATH=/home/llm/models
 
 sudo docker run -itd \
diff --git a/docker/llm/inference/xpu/docker/README.md b/docker/llm/inference/xpu/docker/README.md
index 0ce773c2499..6f9dcec658e 100644
--- a/docker/llm/inference/xpu/docker/README.md
+++ b/docker/llm/inference/xpu/docker/README.md
@@ -6,7 +6,7 @@ docker build \
   --build-arg http_proxy=.. \
   --build-arg https_proxy=.. \
   --build-arg no_proxy=.. \
-  --rm --no-cache -t intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT .
+  --rm --no-cache -t intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT .
 ```
 
 
@@ -17,7 +17,7 @@ To map the `xpu` into the container, you need to specify `--device=/dev/dri` whe
 An example could be:
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \
diff --git a/docker/llm/serving/cpu/docker/Dockerfile b/docker/llm/serving/cpu/docker/Dockerfile
index 045171c284c..f60033b509d 100644
--- a/docker/llm/serving/cpu/docker/Dockerfile
+++ b/docker/llm/serving/cpu/docker/Dockerfile
@@ -1,4 +1,4 @@
-FROM intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
+FROM intelanalytics/ipex-llm-cpu:2.2.0-SNAPSHOT
 
 ARG http_proxy
 ARG https_proxy
diff --git a/docker/llm/serving/cpu/docker/README.md b/docker/llm/serving/cpu/docker/README.md
index 5aa2cb1355e..0aa2471d267 100644
--- a/docker/llm/serving/cpu/docker/README.md
+++ b/docker/llm/serving/cpu/docker/README.md
@@ -6,7 +6,7 @@ docker build \
   --build-arg http_proxy=.. \
   --build-arg https_proxy=.. \
   --build-arg no_proxy=.. \
-  --rm --no-cache -t intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT .
+  --rm --no-cache -t intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT .
 ```
 
 ### Use the image for doing cpu serving
@@ -16,7 +16,7 @@ You could use the following bash script to start the container.  Please be noted
 
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \
diff --git a/docker/llm/serving/cpu/kubernetes/README.md b/docker/llm/serving/cpu/kubernetes/README.md
index 7e8cb0e5b2d..a58a098c08c 100644
--- a/docker/llm/serving/cpu/kubernetes/README.md
+++ b/docker/llm/serving/cpu/kubernetes/README.md
@@ -2,7 +2,7 @@
 
 ## Image
 
-To deploy IPEX-LLM-serving cpu in Kubernetes environment, please use this image: `intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT`
+To deploy IPEX-LLM-serving cpu in Kubernetes environment, please use this image: `intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT`
 
 ## Before deployment
 
@@ -73,7 +73,7 @@ spec:
   dnsPolicy: "ClusterFirst"
   containers:
   - name: fastchat-controller # fixed
-    image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+    image: intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
     imagePullPolicy: IfNotPresent
     env:
     - name: CONTROLLER_HOST # fixed
@@ -146,7 +146,7 @@ spec:
       dnsPolicy: "ClusterFirst"
       containers:
       - name: fastchat-worker # fixed
-        image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+        image: intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
         imagePullPolicy: IfNotPresent
         env:
         - name: CONTROLLER_HOST # fixed
diff --git a/docker/llm/serving/cpu/kubernetes/deployment.yaml b/docker/llm/serving/cpu/kubernetes/deployment.yaml
index d1aaf5c140e..623f3894e59 100644
--- a/docker/llm/serving/cpu/kubernetes/deployment.yaml
+++ b/docker/llm/serving/cpu/kubernetes/deployment.yaml
@@ -24,7 +24,7 @@ spec:
   dnsPolicy: "ClusterFirst"
   containers:
   - name: fastchat-controller # fixed
-    image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+    image: intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
     imagePullPolicy: IfNotPresent
     env:
     - name: CONTROLLER_HOST # fixed
@@ -91,7 +91,7 @@ spec:
       dnsPolicy: "ClusterFirst"
       containers:
       - name: fastchat-worker # fixed
-        image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
+        image: intelanalytics/ipex-llm-serving-cpu:2.2.0-SNAPSHOT
         imagePullPolicy: IfNotPresent
         env:
         - name: CONTROLLER_HOST # fixed
diff --git a/docker/llm/serving/xpu/docker/Dockerfile b/docker/llm/serving/xpu/docker/Dockerfile
index 2938ce4618b..7f2f41bd95d 100644
--- a/docker/llm/serving/xpu/docker/Dockerfile
+++ b/docker/llm/serving/xpu/docker/Dockerfile
@@ -17,7 +17,7 @@ RUN cd /tmp/ && \
     mv /tmp/torch-ccl/dist/oneccl_bind_pt-2.1.100+xpu-cp311-cp311-linux_x86_64.whl /tmp/
 
 
-FROM intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
+FROM intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
 
 ARG http_proxy
 ARG https_proxy
diff --git a/docker/llm/serving/xpu/docker/README.md b/docker/llm/serving/xpu/docker/README.md
index 5b3f00cda9f..d715218d872 100644
--- a/docker/llm/serving/xpu/docker/README.md
+++ b/docker/llm/serving/xpu/docker/README.md
@@ -6,7 +6,7 @@ docker build \
   --build-arg http_proxy=.. \
   --build-arg https_proxy=.. \
   --build-arg no_proxy=.. \
-  --rm --no-cache -t intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT .
+  --rm --no-cache -t intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT .
 ```
 
 
@@ -18,7 +18,7 @@ To map the `xpu` into the container, you need to specify `--device=/dev/dri` whe
 An example could be:
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \