apiVersion: lumbridge/v1
kind: Scene
metadata:
  name: qwen38-dflash-solo
  version: 2
  description: "Production: Qwen3.8-27B vision only, with DFlash2 and durable usage telemetry."
  author: karti
  tags: [brain, vision, sglang, dflash, llm-only, production]

# Spark is the dedicated 27B inference box. ASR and TTS run on metal, and
# separate small-model canaries are intentionally absent from this Scene.
#
# Keep the measured 0.46 static pool. A 0.90 pool did not improve C1-C4
# throughput and left too little page cache. Decoder choice, not unused KV
# capacity, is the speed lever for this workload.
#
# Live A/B on this Spark, 2026-08-31, identical 384-token long-generation probe:
#   aggregate tok/s     C1      C2      C3      C4
#   DSpark 0.90       28.39   50.46   69.59   88.21
#   DFlash2 0.46      31.54   57.09   81.43   85.96  (median of 3)
# DFlash2 wins the common C1-C3 regime by 11-17%. C4 adds only 5.6% over C3,
# so the future job scheduler should normally retain one latency-reserve lane
# and borrow C4 only while queue and TTFT remain healthy.
models:
  - brain-qwen38-dflash

budget_gb: 100
activation:
  order: listed
  wait_healthy: true