# embed-rerank tunables (esh-ml1). Copy to `.env` on the server.
#
# Everything model-shaped here MUST match fv-ml1's stacks/vllm .env: the same
# models, the same vLLM version, the same max-model-len. A drift in the
# embedding model or its version makes this seat's vectors incompatible with
# every index built against fv-ml1's.

# PINNED to fv-ml1's version. Bump both sites together.
VLLM_VERSION=v0.24.0

# Same host ports as fv-ml1 (container listens on 8000).
EMBED_PORT=8001
RERANK_PORT=8013

EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
RERANK_MODEL=BAAI/bge-reranker-v2-m3

# Fractions of the RTX 2000E Ada's 16,380 MiB. fv-ml1 runs 0.03 of a 96 GB
# card (~2.9 GB each); 0.20 here is ~3.2 GB each — the same budget plus a
# little, leaving ~9.5 GB free.
EMBED_GPU_MEM_UTIL=0.20
RERANK_GPU_MEM_UTIL=0.20
EMBED_MAX_MODEL_LEN=8192
RERANK_MAX_MODEL_LEN=8192

# fv-ml1's seats run with no API key (LiteLLM fronts them); match that.
API_KEY=
# Both models are public; no token needed.
HF_TOKEN=