upgrade vLLM to 0.12.0 tag (#4647)

Upgrade vLLM to v0.12.0 tag

- vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
- vLLM main:
86e178f7c4

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

Dockerfile

@@ -48,10 +48,8 @@ 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=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=v0.12.0
+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/ && \
     python3 -m pip uninstall -y triton && \