apiVersion: lumbridge/v1
kind: Scene
metadata:
  name: qwen38-mia
  version: 1
  description: "qwen38 with MiaAI-Lab's full EAGLE tuning (X5 cpuset, host net, GDN pool)."
  author: karti
  tags: [brain, vision, voice, long-context, sglang, benchmark]

# Same model set as `qwen38`; the brain adopts MiaAI-Lab's tuning. The point is
# to find out how much of our ~22 tok/s vs her reported 34.5 is launch config.
# Baseline to beat: EAGLE @ 0.46 decode 22.8 tok/s, toolbench 15/15 @ 1.5 s.
models:
  - brain-qwen38-mia
  - ears
  - voice-vox
  - voice

budget_gb: 100
activation:
  order: listed
  wait_healthy: true