diff --git a/AI/image-list.yml b/AI/image-list.yml
index 78769a81a63dd22e235abff6ecb22d91d58343a8..ba5e7e6131957efc08be54e29d1fd8e8e8a849cd 100644
--- a/AI/image-list.yml
+++ b/AI/image-list.yml
@@ -29,6 +29,7 @@ images:
   llm-faqgen-tgi: opea/llm-faqgen-tgi
   llm-tgi: opea/llm-tgi
   llm-vllm: opea/llm-vllm
+  llm-textgen: opea/llm-textgen
   reranking-tei: opea/reranking-tei
   retriever-redis: opea/retriever-redis
   searchqna: opea/searchqna
diff --git a/AI/opea/codegen-ui/1.2/24.03-lts/Dockerfile b/AI/opea/codegen-ui/1.2/24.03-lts/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..5eb1a5ea78fcdb829cab6cb6bd83c48b999f0e98
--- /dev/null
+++ b/AI/opea/codegen-ui/1.2/24.03-lts/Dockerfile
@@ -0,0 +1,31 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Use node 20.11.1 as the base image
+FROM openeuler/openeuler:24.03-lts
+
+# Update package manager and install Git
+RUN yum update -y && \
+    yum install -y \
+        npm \
+        git
+
+WORKDIR /home/user/
+
+# Copy the front-end code repository
+RUN git clone -b v1.2 https://github.com/opea-project/GenAIExamples.git
+
+# Set the working directory
+WORKDIR /home/user/GenAIExamples/CodeGen/ui/svelte
+
+# Install front-end dependencies
+RUN npm install
+
+# Build the front-end application
+RUN npm run build
+
+# Expose the port of the front-end application
+EXPOSE 5173
+
+# Run the front-end application in preview mode
+CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"]
\ No newline at end of file
diff --git a/AI/opea/codegen-ui/meta.yml b/AI/opea/codegen-ui/meta.yml
index 4cae4dd4a3ff05f2037aaa54695b1cc970e797f2..0e6dfdc00ec532336b9942f33ee6565fe22109d0 100644
--- a/AI/opea/codegen-ui/meta.yml
+++ b/AI/opea/codegen-ui/meta.yml
@@ -1,3 +1,7 @@
 1.0-oe2403lts:
   path: 1.0/24.03-lts/Dockerfile
+  arch: x86_64
+
+1.2-oe2403lts:
+  path: 1.2/24.03-lts/Dockerfile
   arch: x86_64
\ No newline at end of file
diff --git a/AI/opea/codegen/1.2/24.03-lts/Dockerfile b/AI/opea/codegen/1.2/24.03-lts/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..f93be2b75459af0e3184975d9ea5ee7f74bbb27f
--- /dev/null
+++ b/AI/opea/codegen/1.2/24.03-lts/Dockerfile
@@ -0,0 +1,36 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Stage 1: base setup used by other stages
+FROM openeuler/openeuler:24.03-lts AS base
+
+# get security updates
+RUN yum update -y && \
+    yum install -y \
+        git \
+        python python-pip
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user
+
+WORKDIR /home/user/
+
+RUN git clone -b v1.2 https://github.com/opea-project/GenAIComps.git
+
+WORKDIR /home/user/GenAIComps
+
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    pip install --no-cache-dir -r /home/user/GenAIComps/requirements.txt
+
+WORKDIR /home/user/
+
+RUN git clone -b v1.2 https://github.com/opea-project/GenAIExamples.git && \
+    cp GenAIExamples/CodeGen/codegen.py . && \
+    rm -rf GenAIExamples
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user/GenAIComps
+
+USER user
+
+ENTRYPOINT ["python", "codegen.py"]
diff --git a/AI/opea/codegen/meta.yml b/AI/opea/codegen/meta.yml
index 4cae4dd4a3ff05f2037aaa54695b1cc970e797f2..0e6dfdc00ec532336b9942f33ee6565fe22109d0 100644
--- a/AI/opea/codegen/meta.yml
+++ b/AI/opea/codegen/meta.yml
@@ -1,3 +1,7 @@
 1.0-oe2403lts:
   path: 1.0/24.03-lts/Dockerfile
+  arch: x86_64
+
+1.2-oe2403lts:
+  path: 1.2/24.03-lts/Dockerfile
   arch: x86_64
\ No newline at end of file
diff --git a/AI/opea/llm-textgen/1.2/24.03-lts/Dockerfile b/AI/opea/llm-textgen/1.2/24.03-lts/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..a68580f26119aaf38f33a9e0978e4c7b30ad3cf9
--- /dev/null
+++ b/AI/opea/llm-textgen/1.2/24.03-lts/Dockerfile
@@ -0,0 +1,31 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM openeuler/openeuler:24.03-lts
+
+RUN yum update -y && \
+    yum install -y \
+        python python-pip \
+        mesa-libGL \
+        jemalloc-devel \
+        git
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+WORKDIR /home/user/
+
+RUN git clone -b v1.2 https://github.com/opea-project/GenAIComps.git && \
+    cp -r GenAIComps/comps /home/user/comps && \
+    rm -rf GenAIComps
+
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    pip install --no-cache-dir -r /home/user/comps/llms/src/text-generation/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+WORKDIR /home/user/comps/llms/src/text-generation
+
+ENTRYPOINT ["bash", "entrypoint.sh"]
\ No newline at end of file
diff --git a/AI/opea/llm-textgen/meta.yml b/AI/opea/llm-textgen/meta.yml
new file mode 100644
index 0000000000000000000000000000000000000000..ee4b49e9afa63ff59b2371473ff499d093b30722
--- /dev/null
+++ b/AI/opea/llm-textgen/meta.yml
@@ -0,0 +1,3 @@
+1.2-oe2403lts:
+  path: 1.2/24.03-lts/Dockerfile
+  arch: x86_64
\ No newline at end of file
diff --git a/AI/vllm/0.8.3/24.03-lts/Dockerfile b/AI/vllm/0.8.3/24.03-lts/Dockerfile
new file mode 100644
index 0000000000000000000000000000000000000000..8ed829b031c478012ca84441b919b0b2ae73ecb6
--- /dev/null
+++ b/AI/vllm/0.8.3/24.03-lts/Dockerfile
@@ -0,0 +1,19 @@
+# This vLLM Dockerfile is used to construct an image that can build and run vLLM on ARM CPU platform.
+
+FROM openeuler/openeuler:24.03-lts
+
+RUN yum update -y && \
+    yum install -y make gcc gcc-c++ python python-pip python3-devel git vim wget net-tools numactl-devel && \
+    rm -rf /var/cache/yum
+
+WORKDIR /workspace
+
+RUN git clone -b v0.8.3 https://github.com/vllm-project/vllm.git
+
+WORKDIR /workspace/vllm
+
+RUN pip install "cmake>=3.26" wheel packaging ninja "setuptools-scm>=8" numpy
+
+RUN VLLM_TARGET_DEVICE="cpu" pip install -e . --extra-index-url https://download.pytorch.org/whl/cpu
+
+ENTRYPOINT ["python", "-m", "vllm.entrypoints.openai.api_server"]
diff --git a/AI/vllm/README.md b/AI/vllm/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..bd7623aecd2dba1a98aa56f8ac3982191025957e
--- /dev/null
+++ b/AI/vllm/README.md
@@ -0,0 +1,86 @@
+# Quick reference
+
+- The offical vLLM Ascend docker images
+
+- Maintained by: [openEuler CloudNative SIG](https://gitee.com/openeuler/cloudnative)
+
+- Where to get help: [openEuler CloudNative SIG](https://gitee.com/openeuler/cloudnative), [openEuler](https://gitee.com/openeuler/community)
+
+# vLLM | openEuler
+
+Current vLLM docker images are built on the [openEuler](https://repo.openeuler.org/)⁠. This repository is free to use and exempted from per-user rate limits.
+
+vLLM is a fast and easy-to-use library for LLM inference and serving.
+
+Originally developed in the [Sky Computing Lab](https://sky.cs.berkeley.edu/) at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
+
+vLLM is fast with:
+
+- State-of-the-art serving throughputV
+- Efficient management of attention key and value memory with [PagedAttention](https://blog.vllm.ai/2023/06/20/vllm.html)
+- Continuous batching of incoming requests
+- Fast model execution with CUDA/HIP graph
+- Quantizations: [GPTQ](https://arxiv.org/abs/2210.17323), [AWQ](https://arxiv.org/abs/2306.00978), INT4, INT8, and FP8.
+- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer.
+- Speculative decoding
+- Chunked prefill
+
+Read more about vLLM at [vLLM paper](https://arxiv.org/abs/2309.06180) (SOSP 2023) and explore the vLLM technical documentation at [docs.vllm.ai](https://docs.vllm.ai/)
+
+# Supported tags and respective Dockerfile links
+
+The tag of each vLLM docker image is consist of the version of vLLM and the version of basic image. The details are as follows
+
+| Tags | Currently |  Architectures|
+|--|--|--|
+|[0.6.3-oe2403lts](https://gitee.com/openeuler/openeuler-docker-images/blob/master/AI/vllm/0.6.3/24.03-lts/Dockerfile)| vLLM 0.6.3 on openEuler 24.03-LTS | amd64 |
+|[0.8.3-oe2403lts](https://gitee.com/openeuler/openeuler-docker-images/blob/master/AI/vllm/0.8.3/24.03-lts/Dockerfile)| vLLM 0.8.3 on openEuler 24.03-LTS | amd64, arm64 |
+|[0.8.5-oe2403lts](https://gitee.com/openeuler/openeuler-docker-images/blob/master/AI/vllm/0.8.5/24.03-lts/Dockerfile)| vLLM 0.8.5 on openEuler 24.03-LTS | amd64 |
+
+# Usage
+
+## Quick start 1: supported devices
+
+- Intel/AMD x86
+- ARM AArch64
+
+## Quick start 2: setup environment using container
+
+```bash
+# Update the vllm image
+docker run --rm --name vllm -p 8000:8000 -it --entrypoint bash openeuler/vllm-cpu:latest
+```
+## Quick start 3: offline inference
+
+You can use Modelscope mirror to speed up download:
+
+```bash
+export VLLM_USE_MODELSCOPE=true
+```
+
+With vLLM installed, you can start generating texts for list of input prompts (i.e. offline batch inferencing).
+
+Try to run below Python script directly or use `python3` shell to generate texts:
+
+```python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Hello, my name is",
+    "The future of AI is",
+]
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+# The first run will take about 3-5 mins (10 MB/s) to download models
+llm = LLM(model="Qwen/Qwen3-8B")
+
+outputs = llm.generate(prompts, sampling_params)
+
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
+
+# Question and answering
+
+If you have any questions or want to use some special features, please submit an issue or a pull request on [openeuler-docker-images](https://gitee.com/openeuler/openeuler-docker-images)⁠.