# erp-seat — ana-ml2 GPU1. Real .env lives on the host at /opt/docker/compose/erp-seat/.env.
ERP_IMAGE=vllm/vllm-openai:nightly-311b3513af33bc29b4acb2fde2e9313e5e9966a0
ERP_MODEL=/tank/aimodels/G4-MeroMero-26B-A4B-it-uncensored-heretic-NVFP4A16
ERP_SERVED_NAME=G4-MeroMero-26B-A4B-it-uncensored-heretic-NVFP4A16
ERP_CHAT_TEMPLATE=/tank/aimodels/G4-MeroMero-26B-A4B-it-uncensored-heretic-NVFP4A16/chat_template.jinja
ERP_PORT=8021
ERP_GPU_ID=1
# 0.35 x 97.9 GiB = 34 GiB. GPU1 had ~47 GiB free on 2026-09-08 (scriberr/embed/rerank/coder/reward resident).
ERP_GPU_MEM_UTIL=0.30
ERP_MAX_MODEL_LEN=262144
ERP_MAX_NUM_SEQS=32
API_KEY=
# 8.49 GiB -> 534,649 KV tokens -> 2.04x a 262,144 context (operator's KV = 2x rule).
ERP_KV_CACHE_MEMORY=9114000000
ERP_MOE_BACKEND=auto