bstein/titan-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(hermes): correct GPU ownership reference

Browse Source
This commit is contained in:
jenkins 2026-08-02 02:51:35 -03:00
parent 85c5bfe9f4
commit 3cd147538f
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
services/hermes/skills/master-hermes-on-atlas/references/architecture.md
View File

@ -28,7 +28,8 @@ each instance independently ─────> openai-codex/gpt-5.4 fallback
- The configured context length is 64,000 tokens. - The configured context length is 64,000 tokens.
- `hermes-model-gate` is the stable OpenAI-compatible endpoint. - `hermes-model-gate` is the stable OpenAI-compatible endpoint.
- A GPU-owner ConfigMap and controller coordinate Hermes versus Wolf/Moonlight. - A coordination Lease stores whether Hermes or Wolf/Moonlight owns the GPU.
Ariadne has narrowly scoped permission to update that Lease during handoff.
- Wolf ownership makes the gate return a deliberate unavailable response. The - Wolf ownership makes the gate return a deliberate unavailable response. The
Hermes gateway stays alive and can use its configured fallback. Hermes gateway stays alive and can use its configured fallback.
- The two agent pods do not consume titan-24 GPU memory. Ollama does. Agent pods - The two agent pods do not consume titan-24 GPU memory. Ollama does. Agent pods
@ -41,7 +42,7 @@ Verify rather than memorize:
```sh ```sh
hermes status hermes status
hermes fallback list hermes fallback list
kubectl -n hermes get configmap hermes-gpu-owner -o yaml kubectl -n hermes get lease titan-24-gpu-owner -o yaml
kubectl -n hermes get deploy hermes hermes-model-gate hermes-ollama -o wide kubectl -n hermes get deploy hermes hermes-model-gate hermes-ollama -o wide
kubectl -n hermes-chat get deploy hermes-chat -o wide kubectl -n hermes-chat get deploy hermes-chat -o wide
``` ```