# Qwen3.6-35B-A3B VL (official FP8) on ana-ml2 — copy to .env on the host and fill.
# Real .env lives on ana-ml2 at /opt/docker/compose/qwen36-vl/.env (gitignored).
#
# Replaces qwen35-vl (Qwen3.5-9B) 2026-06-14. See compose.yaml header for the
# FP8-over-NVFP4 rationale (vLLM NVFP4 MoE loader broken, #44081) and why this
# uses plain :latest with NO --quantization (pre-quantized checkpoint; a forced
# flag would noise-quantize the vision tower like the old qwen35-vl).

# :latest is fine — the official FP8 checkpoint loads + serves vision correctly
# on 0.19.1 (validated 2026-06-14). NO pinned nightly digest needed.
QWEN_IMAGE=vllm/vllm-openai:latest

QWEN_CONTAINER_NAME=vllm-qwen36
QWEN_MODEL=Qwen/Qwen3.6-35B-A3B-FP8
QWEN_PORT=8007

# GPU 1 = shared with the granite summarizer + embed/rerank/reward trio.
# GPU 0 is kept free for the llama-swap creative-writing hot-swap card.
QWEN_GPU_ID=1

# util 0.42 (~40 GB) — official FP8 weights load in ~34.2 GiB; 0.42 covers
# weights + CUDA-graph + a generous KV pool. Hybrid attn (10 of 40 layers full-
# attn, ~10 KB/tok KV) makes long context nearly free, so max-len is generous.
# Budget (2026-06-14): qwen36 0.42 + granite 0.28 + trio 0.20 = 0.90 total,
# ~10 GB graph headroom. Bring qwen36 up LAST so capture sees the free room.
QWEN_GPU_MEM_UTIL=0.42
QWEN_MAX_MODEL_LEN=131072
# Sampler-warmup OOM guard on the shared GPU (248K vocab × default 1024 seqs is
# a huge transient). 32 is plenty for a vision endpoint.
QWEN_MAX_NUM_SEQS=32

# Optional
HF_TOKEN=
API_KEY=