Bootstrap: docker
From: vllm/vllm-openai:nightly

%labels
    Author herzogfloria
    Description vLLM nightly inference server for Qwen3.5-35B-A3B
    Version 3.0

%environment
    export HF_HOME=/tmp/hf_cache
    export VLLM_USAGE_SOURCE=production

%post
    apt-get update && apt-get install -y --no-install-recommends git && rm -rf /var/lib/apt/lists/*
    pip install --no-cache-dir "transformers @ git+https://github.com/huggingface/transformers.git@main"
    pip install --no-cache-dir huggingface_hub[cli]

%runscript
    exec python3 -m vllm.entrypoints.openai.api_server "$@"

%help
    Apptainer container for serving Qwen3.5-35B-A3B via vLLM (nightly).