inference-builder

Generate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Create GPU-accelerated inference microservices using DeepStream, Triton, vLLM, TensorRT-LLM, or PyTorch backends.

Claude Code1 skill

by NVIDIA73updated 3 weeks ago

Source

$ git clone https://github.com/NVIDIA-AI-IOT/inference_builder

Clone the source, then follow the repository's marketplace instructions for your runtime. The repository root is the plugin root.

Layout

inference-builder/

├── .claude-plugin/plugin.json
└── skills/inference-builder/SKILL.md

Skills1

inference-builderskills/inference-builder/SKILL.md

Generate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Activate when users want to: create GPU-accelerated inference microservices or standalone apps for vision, video, or streaming workloads; write or edit pipeline YAML configs; build Docker images for GPU inference; work with models from NGC or HuggingFace; or deploy with DeepStream, Triton, vLLM, TensorRT-LLM, or PyTorch backends.

Manifests1

.claude-plugin/plugin.json

{
  "name": "inference-builder",
  "description": "Generate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Create GPU-accelerated inference microservices using DeepStream, Triton, vLLM, TensorRT-LLM, or PyTorch backends.",
  "author": {
    "name": "NVIDIA"
  },
  "keywords": [
    "inference",
    "nvidia",
    "deepstream",
    "triton",
    "vllm",
    "tensorrt-llm",
    "pytorch",
    "docker",
    "gpu"
  ]
}