# qwopus3.5-122b (OpenYourMind Qwopus3.5-122B-A10B Kimi-distilled abliterated NVFP4,
# vision-intact) — ana-ml2 GPU 0 tunables. Real .env at /opt/docker/compose/qwopus3.5-122b/.env

# STABLE image + fp8 KV reaches full 256K: the KV pool already held ~222k tokens, so fp8
# (near-lossless, half the bytes/token) clears 262144 with ~2x concurrency. Nightly +
# turboquant_4bit_nc would buy ~5x concurrency at 256K but adds a 4-bit recall risk + FA2
# fallback + nightly instability — not needed for 256K itself.
QWOPUS_IMAGE=vllm/vllm-openai:latest
QWOPUS_CONTAINER_NAME=vllm-qwopus35-122b
QWOPUS_KV_CACHE_DTYPE=fp8

# Reuse :8013 (the bjk110 qwen3.5-122b port, now retired) so the litellm records route
# here unchanged. Served under qwen3.5-122-a10b (the operator's gen records).
QWOPUS_PORT=8013
QWOPUS_SERVED_NAME=qwen3.5-122-a10b
QWOPUS_GPU_ID=0

# Vision-intact NVFP4 (≈82GB incl. bf16 vision tower) on the 96GB Blackwell. CUDA graphs
# ON (no --enforce-eager) for decode throughput. util 0.95 — 0.96 OOM'd by 0.1GB on the
# 3.09GB FusedMoE transient workspace (the hard floor; the card can't reach 0 free), so
# expandable_segments (compose env) reclaims PyTorch fragmentation + 0.95 adds margin.
# max-num-seqs 16 lets short requests fan out (~16x32k); 256K requests pool-limit to ~3.5x.
QWOPUS_GPU_MEM_UTIL=0.95
QWOPUS_MAX_MODEL_LEN=262144
QWOPUS_MAX_NUM_SEQS=16

# Optional upstream vLLM API key (empty = no auth; internal net only).
API_KEY=