# intern-decision — copy to /opt/docker/compose/intern-decision/.env on fv-ml1 (mode 0600).
# Built on fv-ml1 from services/intern-decision-serve (see README "Building").
IMAGE=intern-decision-serve:0.1.0
PORT=8033
HOST_IP=10.251.50.54
# fv-ml1 GPU 1 = the utility card (vllm-coder, erp, meromero, scriberr).
GPU_ID=1
# HARD torch-allocator cap: the single knob that holds the container's WHOLE nvidia-smi footprint
# (CUDA context included) <= 10,300 MiB, the GPU 1 budget next to scriberr (2026-09-30).
#   footprint <= cap + non-allocator overhead = 9,472 MiB + 662 MiB = 10,134 MiB
#   (overhead measured flat at 660-662 MiB with the single inference thread; README "VRAM").
# 9.25 still answers the largest request the API accepts (4 calls x 8,191 tokens) with a 200.
VRAM_CAP_GIB=9.25
# >= 32 characters; source of truth: secret get intern-decision/api-token
INTERN_DECISION_API_TOKEN=