mAi
167999cecf
Convention on mRock is user-units for ML services (whisper-server, mvoice-launcher, comfyui as of today). Switching mGPUmanager too: - systemd/mgpumanager.service: rewritten as a user unit (%h-based WorkingDirectory + ExecStart, WantedBy=default.target). Drops the ProtectSystem/ProtectHome hardening that came from the system-unit template — user units don't need it, and ProtectHome=read-only blocks a user unit's own working dir. - Makefile deploy target: rsync to ~/.config/systemd/user/ on the remote and use systemctl --user, no sudo. README documents the lingering prerequisite (loginctl enable-linger m). - config/consumers.yaml: bind on 0.0.0.0:8770 instead of localhost so mRiver / Tailscale peers can actually reach the broker. Refs: m/mGPUmanager#1 (deploy task).
91 lines
2.0 KiB
YAML
91 lines
2.0 KiB
YAML
listen: 0.0.0.0:8770
|
|
|
|
gpu:
|
|
total_mib: 16376 # RTX 4070 Ti SUPER
|
|
reserved_mib: 1024 # headroom for system/desktop
|
|
poll_interval_seconds: 2
|
|
|
|
routing:
|
|
tts: mvoice
|
|
stt: mvoice # whisper-server is alternative if explicitly requested
|
|
llm: ollama
|
|
image: comfyui
|
|
|
|
# Audio download proxy: any GET under audio_path_prefix is forwarded to this
|
|
# consumer at the same path. wa.sh fetches mvoice's generated WAV this way.
|
|
audio_proxy: mvoice
|
|
audio_path_prefix: /api/audio/
|
|
|
|
consumers:
|
|
mvoice:
|
|
url: http://localhost:8766
|
|
health:
|
|
method: GET
|
|
path: /api/health
|
|
paths:
|
|
tts:
|
|
method: POST
|
|
path: /api/synthesize
|
|
stt:
|
|
method: POST
|
|
path: /api/transcribe
|
|
vram_resident_mib: 2800
|
|
load:
|
|
method: POST
|
|
path: /api/admin/load
|
|
unload:
|
|
method: POST
|
|
path: /api/admin/unload
|
|
can_coexist_with: [whisper-server, ollama]
|
|
priority: 3
|
|
max_concurrency: 1
|
|
|
|
whisper-server:
|
|
url: http://localhost:8178
|
|
health:
|
|
method: GET
|
|
path: /
|
|
paths:
|
|
stt:
|
|
method: POST
|
|
path: /inference
|
|
vram_resident_mib: 2050
|
|
# No HTTP unload; mGPUmanager evicts via systemd restart (Schritt 5).
|
|
systemd_unit: whisper-server.service
|
|
can_coexist_with: [mvoice, ollama]
|
|
priority: 2
|
|
max_concurrency: 1
|
|
|
|
ollama:
|
|
url: http://localhost:11434
|
|
health:
|
|
method: GET
|
|
path: /api/tags
|
|
paths:
|
|
llm:
|
|
method: POST
|
|
path: /api/generate
|
|
# Ollama runs its own LRU keep_alive; we don't track resident VRAM.
|
|
vram_managed: true
|
|
can_coexist_with: [mvoice, whisper-server]
|
|
priority: 2
|
|
max_concurrency: 1
|
|
|
|
comfyui:
|
|
url: http://localhost:8188
|
|
health:
|
|
method: GET
|
|
path: /system_stats
|
|
paths:
|
|
image:
|
|
method: POST
|
|
path: /prompt
|
|
vram_resident_mib: 13000
|
|
unload:
|
|
method: POST
|
|
path: /api/free
|
|
body: '{"unload_models":true,"free_memory":true}'
|
|
can_coexist_with: []
|
|
priority: 1
|
|
max_concurrency: 1
|