Lumbridge Compute — Apache-2.0

scenes/darkroom.scene.yaml

@@ -0,0 +1,27 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: darkroom
+  version: 1
+  description: "Overnight image farm — drops the brain to make room for FLUX.2-klein-9B."
+  author: karti
+  tags: [image, overnight, unattended]
+
+# Drops `brain` so `image` (66 GB, on-hardware measured) fits. ears+voice+music+
+# image commits ~99 GB — tight against the 8 GB admission margin, so this scene
+# needs the full 108 GB ceiling (matching studio/voice-laguna), not the old 100.
+models:
+  - ears
+  - voice
+  - music
+  - image
+
+budget_gb: 108
+activation:
+  order: footprint-asc
+  wait_healthy: true
+
+# Scheduled scenes (planned): hand the box to darkroom overnight, back at 08:00.
+#   schedule:
+#     - activate: "03:00"
+#     - handoff:  "04:00" -> studio

scenes/music.scene.yaml

@@ -0,0 +1,20 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: music
+  version: 1
+  description: "Music studio — ACE-Step XL 4B sft, with ears and voice, no brain."
+  author: karti
+  tags: [music, creative]
+
+# ears 5 + voice 4 + music 24 = 33 GB. Brain-free, so tons of headroom — the clean
+# scene for a music-generation demo when the MoE is not needed.
+models:
+  - ears
+  - voice
+  - music
+
+budget_gb: 100
+activation:
+  order: footprint-asc
+  wait_healthy: true

scenes/studio.scene.yaml

@@ -0,0 +1,22 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: studio
+  version: 2
+  description: "Live voice assistant — ears, brain, mouth, and music."
+  author: karti
+  tags: [assistant, voice, always-on]
+
+# ears 5 + brain 66 + voice 4 + music (XL 4B sft) 24 = 99 GB declared.
+# Empirically validated on the reference node: all four load with ~20 GB MemAvailable free.
+# budget bumped to 108 (box is 121 GB) so the Governor admits the measured-safe set.
+models:
+  - ears
+  - brain
+  - voice
+  - music
+
+budget_gb: 108
+activation:
+  order: footprint-asc      # small first, so brain's big load spike lands last
+  wait_healthy: true

scenes/voice-gemma.scene.yaml

@@ -0,0 +1,22 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: voice-gemma
+  version: 1
+  description: "Efficient voice assistant — Nemotron ASR, Gemma 4 31B, and Chatterbox."
+  author: karti
+  tags: [assistant, voice, efficient, multimodal]
+
+# Gemma's mostly-sliding-window attention keeps its footprint well under brain
+# and brain-laguna's, leaving real headroom in the budget beyond Lumbridge Compute's 8 GB
+# admission margin — useful until brain-gemma's footprint is confirmed on
+# real hardware.
+models:
+  - ears
+  - brain-gemma
+  - voice
+
+budget_gb: 80
+activation:
+  order: footprint-asc
+  wait_healthy: true

scenes/voice-laguna.scene.yaml

@@ -0,0 +1,21 @@
+apiVersion: lumbridge/v1
+kind: Scene
+metadata:
+  name: voice-laguna
+  version: 1
+  description: "High-capability voice assistant — Nemotron ASR, Laguna S 2.1, and Chatterbox."
+  author: karti
+  tags: [assistant, voice, coding, reasoning]
+
+# Laguna replaces Qwen and intentionally excludes ACE-Step. The 108 GB scene
+# budget matches the empirically safe studio ceiling on the reference node while retaining
+# Lumbridge Compute's separate 8 GB admission margin.
+models:
+  - ears
+  - brain-laguna
+  - voice
+
+budget_gb: 108
+activation:
+  order: footprint-asc
+  wait_healthy: true

scenes/voice-qwen.scene.yaml

@@ -0,0 +1,26 @@
+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 as of 2026-08-02, superseded by a newer scene. 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