oskar/homelab-codex-ws
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity
homelab-codex-ws/services/ollama
History
oskar f57a01a20d fix(ollama): disable GPU reservation — no NVIDIA driver on SOLARIA host 
Live cutover 2026-07-15 odkrył: nvidia-smi not found, brak libnvidia-ml
w ldcache — host nigdy nie miał sterownika, natywna Ollama mieliła na CPU.
Sekcja deploy.resources (nvidia) zakomentowana do czasu instalacji sterownika
(backlog). nvidia-container-toolkit doinstalowany na hoście (prerequisite,
brakował w runbooku). Kontener zweryfikowany: 5/5 modeli z bind-mounta,
embed bge-m3 dim=1024, reachable z PIHA przez tailnet.
2026-07-15 19:46:48 +02:00
..
docker-compose.yml fix(ollama): disable GPU reservation — no NVIDIA driver on SOLARIA host 2026-07-15 19:46:48 +02:00
env.example fix(ollama): declare service on SOLARIA, restrict bind, add cutover runbook 2026-07-15 16:09:08 +02:00
healthcheck.sh Add node capability model 2026-05-11 20:46:50 +02:00
README.md Add node capability model 2026-05-11 20:46:50 +02:00
service.yaml Add node capability model 2026-05-11 20:46:50 +02:00

README.md

Ollama

Get up and running with large language models locally.

Usage

Deployed on the solaria node for GPU acceleration.

API is available on port 11434.

Example check:

curl http://localhost:11434/api/tags