# vllm stack tunables. Copy this to `.env` on the server before deploying.
#
#   cp .env.example .env
#   # edit .env with real values
#   docker compose up -d

# Image version — pin for reproducibility (`latest` for edge)
VLLM_VERSION=latest

# Host ports (container always listens on 8000 internally)
EMBED_PORT=8001
RERANK_PORT=8002
REWARD_PORT=8003

# GPU assignment — all services share this GPU
# (ana-ml2 has 0 and 1; default 1 keeps 0 free for heavy LLM work in llama-swap)
GPU_ID=1

# Models — reference by full repo name in API requests
EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B
# Skywork is a local-path AWQ output, not from HF Hub. Bind-mounted into the
# reward container at /local-models — see compose.yaml. No env var here for
# the model path itself since it's hard-coded in the compose command.

# GPU memory split — fractions are of TOTAL GPU memory, not free memory.
# vLLM profiles each service independently, so each slice must be large enough
# to fit that service's model + KV cache with no awareness of the others.
# Setting any one too low causes that container to OOM on KV cache allocation
# with `Available KV cache memory: -X.XX GiB`.
#
# Layout on a 48 GB Ada (~30% headroom kept free; matches current production):
#   EMBED  0.20  (~9.6 GB) — 0.6B Qwen3 embed at 8k ctx; comfortable
#   RERANK 0.20  (~9.6 GB) — 0.6B Qwen3 rerank at 8k ctx; comfortable
#   REWARD 0.30  (~14 GB)  — 8B Skywork AWQ at 16k ctx classify; tune up if OOM
EMBED_GPU_MEM_UTIL=0.20
RERANK_GPU_MEM_UTIL=0.20
REWARD_GPU_MEM_UTIL=0.30

# Context length caps — lower these if VRAM is tight.
# Qwen3-Embedding supports up to 32k; reranker up to 32k.
# Skywork capped at 16k server-side as defense-in-depth; JudgeClient also
# enforces the cap at dispatch time per spec.
EMBED_MAX_MODEL_LEN=8192
RERANK_MAX_MODEL_LEN=8192
REWARD_MAX_MODEL_LEN=16384

# Optional API key — leave blank for no auth (fine on the internal network).
# If set, all three services require `Authorization: Bearer <key>`.
API_KEY=

# HuggingFace token — only needed for gated models in the HF-Hub-loaded
# services (embed/rerank). Reward is local-path, ignores this.
HF_TOKEN=