deepstream-import-vision-model
SkillDocs & knowledgeLets your agent import a vision model from HuggingFace or NGC into an NVIDIA DeepStream pipeline, handling export, engine build, and benchmarking.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the deepstream-import-vision-model skill
About this capability
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
Signals
- GitHub stars
- 3k
- Forks
- 387
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
deepstream-import-vision-model- Source
- github.com/nvidia/skills