sendnrw/glpi-neuroforge-mega
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v1.6.0
release-tag / release-image (push) Successful in 6m50s
Details

Browse Source
This commit is contained in:
groot
2026-09-02 10:26:50 +02:00
parent 8c4ce2d6c2
commit 9a4370e4df
272 changed files with 31244 additions and 5980 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deployments/gpu-subagent/README.md
+13
View File
@@ -0,0 +1,13 @@
# GPU Subagent + Ollama
Runs Ollama on the GPU node, pulls the configured chat and embedding models through two idempotent init services, and registers a GPU worker with capabilities `model.chat` and `model.embed`.
Prerequisites: NVIDIA driver, NVIDIA Container Toolkit and working Docker GPU access.
Edit `NEUROFORGE_MASTER_URL`, then:
```bash
./preflight.sh
docker compose --profile monitoring up -d
```
Ollama is intentionally exposed on port 11434 so the Master Agent/Knowledge services can use this GPU node directly. Restrict ports 11434, 9100 and 9400 to the Master/Prometheus host with a firewall.