NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
1 skill
Build DeepStream GStreamer pipelines interactively. Collects input source, inference, tracker, and output preferences, then assembles a ready-to-run gst-launch-1.0 pipeline using BM25 retrieval over 270+ verified pipelines (zero external dependencies).
1 skill
DeepStream SOP compliance monitoring — 18-section reference covering GPU-accelerated event boundary detection (GEBD, e.g. DDM) + VLM-based SOP checking with Cosmos Reason 1 or 2, Triton CAPI, Basler GigE camera (Pylon SDK + emulation), Kafka/SSE output, and RTSP streaming output.
1 skill
Plan and configure repo-native Nemotron customization workflows from existing steps: curate/nemo_curator JSONL cleaning, translate/nemo_curator corpus translation, sft/automodel, peft/automodel, sft/megatron_bridge, peft/megatron_bridge, pretrain/CPT, rl/nemo_rl alignment, byob/mcq benchmarks, convert/megatron_to_hf and other checkpoint conversion, optimize/modelopt, eval/model_eval, env/env_toml profiles, and end-to-end pipelines.
1 skill
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you find the right skills to help in building NVIDIA-powered workflows.
1 skill