# qwen-image-bench (flukethoughts/Qwen-Image-Bench-NVFP4) — ana-ml2 GPU 1 tunables.
# Real .env lives at /opt/docker/compose/qwen-image-bench/.env.

QIB_IMAGE=vllm/vllm-openai:latest
QIB_CONTAINER_NAME=vllm-qwen-image-bench

# Own port (8007=qwen36 [downed], 8010=qwen-gen, 8011=selene — 8014 free).
QIB_PORT=8014
QIB_GPU_ID=1

# Shared GPU 1 (granite/selene/embed/rerank/reward + this). util is a fraction of
# TOTAL (96GB), so it must clear the ~20GB weight floor + leave KV: 0.22 (~21GB) left
# ~nothing for KV and crash-looped ("no available memory for cache blocks"). 0.32
# (~31GB → ~9GB KV) fits the ~37GB freed by downing qwen36 (cf. qwen36's own 0.34).
QIB_GPU_MEM_UTIL=0.32
QIB_MAX_MODEL_LEN=32768
QIB_MAX_NUM_SEQS=8

# Optional upstream vLLM API key (empty = no auth; internal net only).
API_KEY=