diff --git a/.github/workflows/image_openeuler.yml b/.github/workflows/image_openeuler.yml
index 320824b..4654d4b 100644
--- a/.github/workflows/image_openeuler.yml
+++ b/.github/workflows/image_openeuler.yml
@@ -93,7 +93,5 @@ jobs:
         labels: ${{ steps.meta.outputs.labels }}
         tags: ${{ steps.meta.outputs.tags }}
         file: Dockerfile.openEuler
-        # TODO: support and enable custom ops build for openEuler
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
-          COMPILE_CUSTOM_KERNELS=0
diff --git a/Dockerfile.openEuler b/Dockerfile.openEuler
index cce429c..538d533 100644
--- a/Dockerfile.openEuler
+++ b/Dockerfile.openEuler
@@ -23,9 +23,8 @@ ARG COMPILE_CUSTOM_KERNELS=1
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
 
 RUN yum update -y && \
-    yum install -y python3-pip git vim wget net-tools && \
-    rm -rf /var/cache/yum &&\
-    rm -rf /tmp/*
+    yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
+    rm -rf /var/cache/yum
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
@@ -35,21 +34,23 @@ COPY . /workspace/vllm-ascend/
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=main
+ARG VLLM_TAG=v0.8.4
 
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /workspace/vllm
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install /workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN python3 -m pip uninstall -y triton
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+    python3 -m pip uninstall -y triton && \
+    python3 -m pip cache purge
 
 # Install vllm-ascend
 RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
     source /usr/local/Ascend/nnal/atb/set_env.sh && \
-    export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib:$LD_LIBRARY_PATH && \
-    export LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/lib64:$LIBRARY_PATH && \
-    python3 -m pip install -v /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/
+    export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
+    python3 -m pip install -v -e /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+    python3 -m pip cache purge
 
 # Install modelscope (for fast download) and ray (for multinode)
-RUN python3 -m pip install modelscope ray
+RUN python3 -m pip install modelscope ray && \
+    python3 -m pip cache purge
 
-CMD ["/bin/bash"]
+CMD ["/bin/bash"]
\ No newline at end of file