diff --git a/.github/workflows/image_openeuler.yml b/.github/workflows/image_openeuler.yml
index da94cac8f3..f6f7cea333 100644
--- a/.github/workflows/image_openeuler.yml
+++ b/.github/workflows/image_openeuler.yml
@@ -88,6 +88,8 @@ jobs:
       uses: docker/build-push-action@v6
       with:
         platforms: linux/amd64,linux/arm64
+        # use the current repo path as the build context, ensure .git is contained
+        context: .
         # only trigger when tag, branch/main push
         push: ${{ github.event_name == 'push' && github.repository_owner == 'vllm-project' }}
         labels: ${{ steps.meta.outputs.labels }}
diff --git a/.github/workflows/image.yml b/.github/workflows/image_ubuntu.yml
similarity index 88%
rename from .github/workflows/image.yml
rename to .github/workflows/image_ubuntu.yml
index ba9fecad39..5cdf076839 100644
--- a/.github/workflows/image.yml
+++ b/.github/workflows/image_ubuntu.yml
@@ -16,7 +16,7 @@ on:
       - 'main'
       - '*-dev'
     paths:
-      - '.github/workflows/image.yml'
+      - '.github/workflows/image_ubuntu.yml'
       - 'Dockerfile'
       - 'vllm_ascend/**'
   push:
@@ -27,13 +27,13 @@ on:
     tags:
       - 'v*'
     paths:
-      - '.github/workflows/image.yml'
+      - '.github/workflows/image_ubuntu.yml'
       - 'Dockerfile'
       - 'vllm_ascend/**'
 jobs:
 
   build:
-    name: vllm-ascend image
+    name: vllm-ascend Ubuntu image
     runs-on: ubuntu-latest
 
     steps:
@@ -72,9 +72,6 @@ jobs:
 
     - name: Build - Set up QEMU
       uses: docker/setup-qemu-action@v3
-      # TODO(yikun): remove this after https://github.com/docker/setup-qemu-action/issues/198 resolved
-      with:
-        image: tonistiigi/binfmt:qemu-v7.0.0-28
 
     - name: Build - Set up Docker Buildx
       uses: docker/setup-buildx-action@v3
@@ -91,12 +88,11 @@ jobs:
       uses: docker/build-push-action@v6
       with:
         platforms: linux/amd64,linux/arm64
-        cache-from: type=gha
-        cache-to: type=gha,mode=max
+        # use the current repo path as the build context, ensure .git is contained
         context: .
         # only trigger when tag, branch/main push
         push: ${{ github.event_name == 'push' && github.repository_owner == 'vllm-project' }}
         labels: ${{ steps.meta.outputs.labels }}
         tags: ${{ steps.meta.outputs.tags }}
         build-args: |
-            PIP_INDEX_URL=https://pypi.org/simple
+          PIP_INDEX_URL=https://pypi.org/simple
diff --git a/Dockerfile b/Dockerfile
index fd53b1f1af..dbfff4f512 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -29,19 +29,19 @@ RUN apt-get update -y && \
 
 WORKDIR /workspace
 
-COPY . /workspace/vllm-ascend/
+COPY . /vllm-workspace/vllm-ascend/
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.7.3
-RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /workspace/vllm
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip cache purge
 
 # Install vllm-ascend
-RUN python3 -m pip install -e /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN python3 -m pip install -e /vllm-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)
diff --git a/Dockerfile.openEuler b/Dockerfile.openEuler
index 0f9403cf7f..0365969745 100644
--- a/Dockerfile.openEuler
+++ b/Dockerfile.openEuler
@@ -25,19 +25,19 @@ RUN yum update -y && \
 
 WORKDIR /workspace
 
-COPY . /workspace/vllm-ascend/  
+COPY . /vllm-workspace/vllm-ascend/  
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.7.3
-RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /workspace/vllm
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip cache purge
 
 # Install vllm-ascend
-RUN python3 -m pip install -e /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN python3 -m pip install -e /vllm-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)