# 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, RIGHT-SIZED 2026-06-05 to free room for the granite
# summarizer's CUDA graphs + a LoRA hedge. The trio was wildly over-provisioned:
# embed ran a 5.89x KV pool, reward 3.90x — pure waste for utility models that
# need ~1.5x. Trimmed to free ~10 GB. (Utilization = fraction of TOTAL GPU mem;
# each service profiles independently. Too low → that container OOMs on KV with
# `Available KV cache memory: -X.XX GiB`.)
#   EMBED  0.07  (~3.4 GB) — 0.6B Qwen3 embed @8k; 1.1GB weights + ~2GB KV (~3x)
#   RERANK 0.07  (~3.4 GB) — 0.6B Qwen3 rerank @8k; comfortable
#   REWARD 0.18  (~8.6 GB) — 8B Skywork AWQ @16k; 4.4GB weights + ~3.5GB KV (~1.5x)
EMBED_GPU_MEM_UTIL=0.07
RERANK_GPU_MEM_UTIL=0.07
REWARD_GPU_MEM_UTIL=0.18

# 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=

# === granite-4.1-8b (production summarizer / dreaming agent) ===
# Replaced phi4-mini 2026-06-05 (Granite 4.1 8B beat phi4 on precision in
# brokkr's R15 P03 model-fitness eval). Same GPU-1 slot, reusing phi4's port.
GRANITE_PORT=8004
# GPU 1 — co-located with the embed/rerank/reward trio. With phi4 retired, GPU 1
# has ~19 GB free; granite at 56K + FP8 KV needs ~15-16 GB → ~2-3 GB margin.
# NOTE: llama-swap also uses GPU 1 dynamically — a large swap-in could contend;
# pin llama-swap to GPU 0 for clean separation (follow-up).
GRANITE_GPU_ID=1
# Official IBM pre-quantized FP8 (compressed-tensors) — calibrated, ~9.6 GB,
# loaded directly (FP8 native on Ada cc 8.9). Fallback to vLLM-native dynamic FP8
# from BF16: GRANITE_MODEL=ibm-granite/granite-4.1-8b + GRANITE_QUANT=fp8.
GRANITE_MODEL=ibm-granite/granite-4.1-8b-fp8
GRANITE_QUANT=compressed-tensors
GRANITE_SERVED_NAME=granite-4.1-8b
# 50K ctx (51200) — matches phi4's window. Deliberately NOT maxed: leaves ~3 GB
# on GPU 1 as a hedge for future Granite-LoRA serving (--enable-lora needs ~2-3 GB)
# / a holistic GPU-1 retune of the embed/rerank/reward trio. KV @50K fp8 ≈ 4.2 GB;
# +9.6 weights +~2.4 overhead ≈ 16.2 GB. Granite 4.1 supports up to 131072.
GRANITE_MAX_MODEL_LEN=51200
# FP8 KV cache (native on Ada cc 8.9). At 50K ≈ ~4.2 GB (vs ~8.4 GB at fp16).
GRANITE_KV_CACHE_DTYPE=fp8
# Target ~16.2 GB of GPU 1's ~19 GB free: weights 9.6 + KV 4.2 + overhead ~2.4.
# 0.36×46≈16.6 GB budget (covers it with slack). Confirm vs vLLM's first-boot KV log.
GRANITE_GPU_MEM_UTIL=0.36