Switch vLLM from main to v0.18.2rc0 for CUDA 13.2 compatibility

vllm/Dockerfile

@@ -117,8 +117,8 @@ RUN apt-get update && apt-get install -y build-essential cmake gcc && \
 # Build vLLM from source
 # ==============================================================================
 FROM build-base AS build-vllm
-# Bleeding edge: build from main branch
-ARG VLLM_REF=main
+# vLLM version to build
+ARG VLLM_REF=v0.18.2rc0
 # Install ccache for faster compilation
 RUN apt-get update && apt-get install -y ccache
 RUN git clone https://github.com/vllm-project/vllm.git