27 lines
874 B
YAML
27 lines
874 B
YAML
apiVersion: lumbridge/v1
|
|
kind: Scene
|
|
metadata:
|
|
name: voice-qwen
|
|
version: 2
|
|
description: "Superseded by a newer scene on this node. Kept only because it is still the recorded fallback."
|
|
author: karti
|
|
tags: [assistant, voice, low-latency, deprecated]
|
|
|
|
# DEPRECATED — renamed to "downstream" on 2026-08-02. This file is retained solely
|
|
# because last_known_good still points at it; delete once the fallback rolls forward.
|
|
#
|
|
# Its ordering was made brain-first to match its successor. `brain` now runs MTP, whose
|
|
# KV-cache profiling spike is not bounded by gpu-memory-utilization; the old
|
|
# footprint-asc order would start voice+ears first and leave brain short enough
|
|
# to trip the 3GB watchdog floor. A fallback that cannot come up is worse than
|
|
# no fallback.
|
|
models:
|
|
- brain
|
|
- ears
|
|
- voice
|
|
|
|
budget_gb: 100
|
|
activation:
|
|
order: listed
|
|
wait_healthy: true
|