poprhythm
cd127a23e0
obico's own comment already notes its :cuda tag falls back to CPU inference on this driver/GPU combo, but it was still reserving 826MB of VRAM it never used productively. That squeeze was forcing ollama to offload only 20/29 model layers to GPU, pushing the rest onto CPU and causing severe latency (multi-minute LLM calls) that stalled SUB/WAVE's track picking. Claude-Session: https://claude.ai/code/session_01L7Rwa6guD5wK8F8tWQwcJX
46 lines
1.4 KiB
YAML
46 lines
1.4 KiB
YAML
services:
|
|
obico-redis:
|
|
image: redis:7.2-alpine
|
|
container_name: obico-redis
|
|
restart: unless-stopped
|
|
networks:
|
|
- obico-internal
|
|
|
|
obico:
|
|
# :cuda tag falls back to CPU anyway on this GPU (libcudart.so.11.0
|
|
# required; GTX 1660 SUPER with driver 590 has CUDA 12) - adequate for a
|
|
# single printer. No GPU reservation here so it doesn't reserve VRAM
|
|
# ollama needs for its own model (was forcing partial CPU offload there).
|
|
image: ghcr.io/imagegenius/obico:cuda
|
|
container_name: obico
|
|
restart: unless-stopped
|
|
depends_on:
|
|
- obico-redis
|
|
environment:
|
|
- PUID=1000
|
|
- PGID=1000
|
|
- TZ=America/New_York
|
|
- REDIS_URL=redis://obico-redis:6379
|
|
# HOST_IP must exactly match the URL used to access Obico (no trailing slash, no http://)
|
|
# Wrong value causes HTTP 500 errors on all page loads
|
|
- HOST_IP=obico.kolpacksoftware.com
|
|
- SITE_USES_HTTPS=True
|
|
- CSRF_TRUSTED_ORIGINS=["https://obico.kolpacksoftware.com"]
|
|
- DJANGO_SECRET_KEY=${DJANGO_SECRET_KEY}
|
|
# Set to True temporarily to register your account, then back to False
|
|
- ACCOUNT_ALLOW_SIGN_UP=False
|
|
volumes:
|
|
- /srv/obico/config:/config
|
|
- /srv/obico/config/model_cache:/model_cache/ml_api
|
|
ports:
|
|
- "3334:3334"
|
|
networks:
|
|
- npm-network
|
|
- obico-internal
|
|
|
|
networks:
|
|
npm-network:
|
|
external: true
|
|
obico-internal:
|
|
driver: bridge
|