domains / families / science / rtvi-vlm-customize-model
rtvi-vlm-customize-model
separate
How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks.
When to use
- repoint the VSS Alerts Blueprint to a different VLM endpoint,
- run `rtvi-vlm` standalone with either an OpenAI-compatible endpoint or the in-container vLLM path,
- fix the assumption that changing one VLM config automatically updates `rtvi-vlm`, `vlm-as-verifier`, and `vss-agent`.
When not to use
- CV detector swaps inside vss-rt-cv
Skill page
Source
| Repository | Path |
|---|
| NVIDIA/skills | skills/rtvi-vlm-customize-model/SKILL.md |