[CI] Refactor to speedup image building and CI Installation (#6708)

### What this PR does / why we need it?
1. Refactor  image workflow using cache-from to speedup builds

![build](https://github.com/user-attachments/assets/02135c12-0069-44f8-a3ec-5c2b4282448a)

Simultaneously refactored all Dockerfiles by placing layers that rarely
change before those that change frequently, improving build cache hit
rate.

2. Refactor E2E test using vllm-ascend container images, to skip C
compile while no C code are changed

![e2e](https://github.com/user-attachments/assets/49f5b166-0df3-41e1-8f71-b3bbbed17cfd)

In this case, the job will only replace the source code of vllm-ascend
and install `requirements-dev.txt`, saving about 10min before tests

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
9562912cea

Signed-off-by: wjunLu <wjunlu217@gmail.com>

Dockerfile.a3

@@ -19,24 +19,20 @@ FROM quay.io/ascend/cann:8.5.0-a3-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG MOONCAKE_TAG=v0.3.8.post1
-ARG SOC_VERSION="ascend910_9391"
 
-COPY . /vllm-workspace/vllm-ascend/
-# Define environments
+COPY ./tools/mooncake_installer.sh /vllm-workspace/
+
 ENV DEBIAN_FRONTEND=noninteractive
-ENV SOC_VERSION=$SOC_VERSION \
-    TASK_QUEUE_ENABLE=1 \
-    OMP_NUM_THREADS=1
-
-RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 WORKDIR /workspace
 
-# Install Mooncake dependencies
+# Install clang-15 (for triton-ascend) and Mooncake
 RUN apt-get update -y && \
-    apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev libjemalloc2 && \
+    apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev libjemalloc2 clang-15 && \
+    update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20 && \
+    update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20 && \
     git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
-    cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
+    mv /vllm-workspace/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
     cd /vllm-workspace/Mooncake && bash mooncake_installer.sh -y && \
     ARCH=$(uname -m) && \
     source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
@@ -47,17 +43,28 @@ RUN apt-get update -y && \
     rm -rf /var/cache/apt/* && \
     rm -rf /var/lib/apt/lists/*
 
+# Install modelscope (for fast download) and ray (for multinode)
+RUN pip config set global.index-url ${PIP_INDEX_URL} && \
+    python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
+    python3 -m pip cache purge
+
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.16.0
-RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm && \
+    # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
+    VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 
 # Install vllm-ascend
-# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
+ARG SOC_VERSION="ascend910_9391"
+ENV DEBIAN_FRONTEND=noninteractive
+ENV SOC_VERSION=$SOC_VERSION \
+    TASK_QUEUE_ENABLE=1 \
+    OMP_NUM_THREADS=1
+COPY . /vllm-workspace/vllm-ascend/
+
 RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
     source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
     source /usr/local/Ascend/nnal/atb/set_env.sh && \
@@ -65,18 +72,7 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip cache purge
 
-# Install clang-15 (for triton-ascend)
-RUN apt-get update -y && \
-    apt-get -y install clang-15 && \
-    update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20 && \
-    update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20 && \
-    rm -rf /var/cache/apt/* && \
-    rm -rf /var/lib/apt/lists/*
-
-# Install modelscope (for fast download) and ray (for multinode)
-RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
-    python3 -m pip cache purge
-
+# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
 RUN echo "export LD_PRELOAD=/usr/lib/$(uname -m)-linux-gnu/libjemalloc.so.2:$LD_PRELOAD" >> ~/.bashrc
 
 CMD ["/bin/bash"]