# Qwen3.5-9B VL (FP8) on ana-ml2 — copy to .env on the host and fill.
# Real .env lives on ana-ml2 at /opt/docker/compose/qwen35-vl/.env (gitignored).

# Pinned nightly digest — carries the Qwen3.5-VL vision-FP8 exclusion fix that
# :latest (v0.19.1) lacks. Re-pin to :latest once the fix reaches a stable
# release (see README + compose header).
QWEN_IMAGE=vllm/vllm-openai@sha256:49211ab2155b21a2dc35f3583f5b545f5e55e77daf8f86df49977c71d5f2f528

QWEN_CONTAINER_NAME=vllm-qwen35
QWEN_MODEL=Qwen/Qwen3.5-9B
QWEN_SERVED_NAME=qwen3.5-9b-fp8
QWEN_PORT=8007

# GPU 1 = shared with the granite summarizer + embed/rerank/reward trio.
# GPU 0 is kept free for hot-reloading large models.
QWEN_GPU_ID=1

# 0.40 (~38 GB) — above the ~34 GB start floor, ~10 GB card headroom over prod.
# On this shared card vLLM needs free >= util*total, so util is capped ~0.51.
QWEN_GPU_MEM_UTIL=0.40
QWEN_MAX_MODEL_LEN=32768

# Optional
HF_TOKEN=
API_KEY=