SENTINEL_IMAGE=vllm/vllm-openai:nightly-e9d1398d9edfd90fcc1cf783805240e3effec013 API_KEY= SENTINEL_GPU_ID=0 SENTINEL_PORT=8025 SENTINEL_MODEL=/tank/aimodels/sentinel-r3-nvfp4-mixed SENTINEL_GPU_MEM_UTIL=0.40 SENTINEL_MAX_MODEL_LEN=163840 SENTINEL_KV_CACHE_MEMORY=8589934592 SENTINEL_MAX_NUM_BATCHED_TOKENS=4096 SENTINEL_DRAFT_MODEL=/tank/aimodels/qwen38-27b-dflash2-drafter