FROM nvidia/cuda:12.9.0-base-ubuntu22.04

RUN apt-get update -y \
    && apt-get install -y python3-pip

RUN ldconfig /usr/local/cuda-12.9/compat/

# Install Python dependencies
COPY builder/requirements.txt /requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip \
    python3 -m pip install --upgrade pip && \
    python3 -m pip install --upgrade -r /requirements.txt

# Install vLLM
RUN python3 -m pip install vllm==0.15.0

# Setup for Option 2: Building the Image with the Model included
ARG MODEL_NAME=""
ARG TOKENIZER_NAME=""
ARG BASE_PATH="/runpod-volume"
ARG QUANTIZATION=""
ARG MODEL_REVISION=""
ARG TOKENIZER_REVISION=""
ARG VLLM_NIGHTLY="true"

ENV MODEL_NAME=$MODEL_NAME \
    MODEL_REVISION=$MODEL_REVISION \
    TOKENIZER_NAME=$TOKENIZER_NAME \
    TOKENIZER_REVISION=$TOKENIZER_REVISION \
    BASE_PATH=$BASE_PATH \
    QUANTIZATION=$QUANTIZATION \
    HF_DATASETS_CACHE="${BASE_PATH}/huggingface-cache/datasets" \
    HUGGINGFACE_HUB_CACHE="${BASE_PATH}/huggingface-cache/hub" \
    HF_HOME="${BASE_PATH}/huggingface-cache/hub" \
    HF_HUB_ENABLE_HF_TRANSFER=0 

ENV PYTHONPATH="/:/vllm-workspace"

RUN if [ -n "${VLLM_NIGHTLY}" ]; then \
    pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly && \
    apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/* && \
    pip install git+https://github.com/huggingface/transformers.git; \
fi


COPY src /src
RUN --mount=type=secret,id=HF_TOKEN,required=false \
    if [ -f /run/secrets/HF_TOKEN ]; then \
    export HF_TOKEN=$(cat /run/secrets/HF_TOKEN); \
    fi && \
    if [ -n "$MODEL_NAME" ]; then \
    python3 /src/download_model.py; \
    fi

# Start the handler
CMD ["python3", "/src/handler.py"]
