# Generated from a declarative template. Nothing here asks for an integration:
# the platform reads the label the image carries and attaches its serving layer
# to the `vllm serve` below.
FROM vllm/vllm-openai:v0.28.0

ENV MODEL=nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 \
    MODEL_REVISION=a9904d24bcc1d289a1950fa9d2b978c47cf903b9 \
    MAX_MODEL_LEN=8192 \
    GPU_MEMORY_UTILIZATION=0.85 \
    HF_HOME=/weights \
    PORT=8080

EXPOSE 8080

ENTRYPOINT ["/bin/sh", "-c", \
  "exec vllm serve \"$MODEL\" --revision \"$MODEL_REVISION\" --port \"$PORT\" --max-model-len \"$MAX_MODEL_LEN\" --gpu-memory-utilization \"$GPU_MEMORY_UTILIZATION\""]
