Vss Benchmark Vlm QA

Benchmark video Q&A accuracy and latency of a deployed RT-VLM (Cosmos Reason 3) via vss vlm run, using questions and videos from the DSS vss-devx-base dataset. Replaces the deprecated nat eval / vss-agent QA path. Not for tool-calling or trajectory evaluation, and not for LVS summarization throughput.

NVIDIA-AI-Blueprints Updated

File contents

nvidia-ai-blueprints/video-search-and-summarization commit 3a202b443a

Frequently asked questions

npx get-skill add nvidia-ai-blueprints/vss-benchmark-vlm-qa