# vllm-qwen3 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

# GPU assignment — both services share this GPU
# (ana-ml2 has 0 and 1; default 1 keeps 0 free for heavy LLM work)
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

# GPU memory split — fractions are of TOTAL GPU memory, not free memory.
# When two vLLM services share a GPU, each profiler needs its own slice to
# fit both the model and KV cache, so small values cause the second-to-start
# service to OOM on KV cache allocation. 0.40 + 0.40 leaves ~20% headroom
# and is comfortably above the minimum for two 0.6B Qwen3 models at 8k ctx.
EMBED_GPU_MEM_UTIL=0.40
RERANK_GPU_MEM_UTIL=0.40

# Context length caps — lower these if VRAM is tight.
# Qwen3-Embedding supports up to 32k; reranker up to 32k.
EMBED_MAX_MODEL_LEN=8192
RERANK_MAX_MODEL_LEN=8192

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

# HuggingFace token — only needed for gated models
HF_TOKEN=