adapt to vllm-ascend v0.18.0rc1

Dockerfile

@@ -65,6 +65,8 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     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/vnpu_offload && \
+    make install && make clean && \
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     \
     if [ "$(uname -i)" = "x86_64" ]; then python3 -m pip uninstall -y triton; fi && \
@@ -84,6 +86,9 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${PTA_WHEEL}" && \
     python3 -m pip cache purge
 
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn \
+    VLLM_ASCEND_ENABLE_VNPU=1
+
 # Install clang-15 (for triton-ascend)
 RUN apt-get update -y && \
     apt-get -y install clang-15 && \