# Selene 1 Mini 8B judge (FP8) on ana-ml2 GPU 1 — copy to .env on the host.
# Real .env lives on ana-ml2 at /opt/docker/compose/selene/.env (gitignored).
#
# See compose.yaml header for the FP8-over-NVFP4 (judge-fidelity) rationale.

# 0.23.0 — Llama 3.1 + dynamic fp8 is rock-solid here (same digest as qwen36).
SELENE_IMAGE=vllm/vllm-openai@sha256:6d8429e38e3747723ca07ee1b17972e09bb9c51c4032b266f24fb1cc3b22ed8f

SELENE_CONTAINER_NAME=vllm-selene
SELENE_MODEL=AtlaAI/Selene-1-Mini-Llama-3.1-8B
SELENE_PORT=8011

# GPU 1 = shared with qwen36 (NVFP4) + granite + embed/rerank/reward.
SELENE_GPU_ID=1

# util 0.17 (~16.3 GB) — grown from 0.13 to give Domari's now-live judge role real
# concurrency headroom (KV ~6.3 GiB → ~3.2x at 32K, far more at short eval ctx).
# 8.51 GiB FP8 weights + graph + the rest is KV. (0.12 crashed — KV < one 32K req;
# 0.13 was the minimum-fit; 0.17 is the comfortable judge size.) ctx 32768.
SELENE_GPU_MEM_UTIL=0.17
SELENE_MAX_MODEL_LEN=32768
SELENE_MAX_NUM_SEQS=16

# Optional — checkpoint is ungated (Apache-2.0).
HF_TOKEN=
API_KEY=