# Qwen3.6-35B-A3B VL (official NVFP4) 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).
#
# Swapped FP8→NVFP4 2026-06-15 (the nvidia ModelOpt NVFP4 MoE now loads on vLLM
# 0.23.0 — #44081 fixed). See compose.yaml header for the full rationale + the
# comfy-dev vision A/B that cleared it + the GPU-1 rebalance.

# PINNED by digest — NVFP4 needs vLLM >= 0.23.0 (the related ModelOpt NVFP4 MoE
# path broke on 0.19.1/0.22.0). Pin guards against a :latest regression. This
# digest = 0.23.0, validated to load + serve this checkpoint (vision incl.).
QWEN_IMAGE=vllm/vllm-openai@sha256:6d8429e38e3747723ca07ee1b17972e09bb9c51c4032b266f24fb1cc3b22ed8f

QWEN_CONTAINER_NAME=vllm-qwen36
QWEN_MODEL=nvidia/Qwen3.6-35B-A3B-NVFP4
QWEN_PORT=8007

# GPU 1 = shared with the granite summarizer + embed/rerank/reward trio.
# (GPU 0 now hosts Mistral Small 4, not the old llama-swap card.)
QWEN_GPU_ID=1

# util 0.32 (~31 GB) — NVFP4 weights load in ~20.4 GiB; 0.32 covers weights +
# fp16 KV + CUDA-graph. fp16 KV (compose drops --kv-cache-dtype fp8): the NVFP4
# swap freed enough room to run full-precision KV. Hybrid attn (10/40 full-attn)
# keeps even fp16 KV cheap. GPU-1 budget (2026-06-15 rebalance, pinned): qwen36
# GPU-1 budget (2026-06-16): qwen36 0.34 (grown from 0.32 for the arbo-judge +
# worldtree actor/echo + gateway load) + granite 0.34/131072 + selene 0.17 + trio
# 0.16. Nominal sum >1.0 but the pooling models + granite under-use their util, so
# it fits with ~5-6 GB physical free. Recreate ONE service at a time (profiling race).
QWEN_GPU_MEM_UTIL=0.34
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 — checkpoint is ungated.
HF_TOKEN=
API_KEY=