update other platforms' Dockerfile

Dockerfile.a3

@@ -20,11 +20,13 @@ FROM quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
 ARG MOONCAKE_TAG=v0.3.7.post2
+ARG SOC_VERSION="ascend910_9391"
 
 COPY . /vllm-workspace/vllm-ascend/
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
-ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS} \
+    SOC_VERSION=$SOC_VERSION
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
@@ -58,9 +60,15 @@ 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 && \
     export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
+    cd /vllm-workspace/vllm-ascend/csrc/idle_offload && \
+    make install && make clean && \
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip cache purge
 
+ENV VLLM_ASCEND_ENABLE_NZ=0 \
+    VLLM_WORKER_MULTIPROC_METHOD=spawn \
+    VLLM_ASCEND_ENABLE_IDLE_OFFLOAD=1
+
 # 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