Dev & Engineering ✓ NVIDIA · Official deepstreampipeline-profilingnsight-systemsnvtxnvidia-smifps-benchmarkingvideo-analytics

DeepStream Pipeline Profiler

Measure DeepStream pipelines and derive performance-focused configurations.

FollowSkills review · FSRS-2.0
Not recommended
48/ 100 5-point scale 2.4 / 5
Trust14 / 25 · 2.8/5

The documentation restricts operation to terminal tools, requires read-before-edit, discloses NVTX coverage limits, and provides configuration checks and prebuild steps. However, it permits silent configuration edits, lacks confirmation, rollback, and sensitive RTSP/video data-flow guidance, and suggests sudo or --privileged fallbacks, so points are deducted.

Reliability7 / 20 · 1.8/5

The six-stage flow, failure branches, and diagnostic signals are fairly detailed. Nevertheless, the batch sweep differs between SKILL.md (including 32) and README.md (ending at 16), queue sizing conflicts between ×4 and ×2, referenced scripts/tests are not supplied, and key paths cannot be reproduced statically; therefore the score stays below the static ceiling.

Adaptability9 / 15 · 3.0/5

Trigger conditions, non-trigger cases, model-dimension discovery, and source types are clearly described. Fit is limited by hard dependencies on a DeepStream 9.0 container, Nsight Systems, a GPU, and nvidia-smi; Chinese-language support is not addressed, and the core container dependency may be difficult to reach from mainland-China networks.

Convention8 / 15 · 2.7/5

SKILL.md, README, references, and evaluation material provide useful progressive structure, versioning, ownership, licensing, related skills, and limitations. Deductions apply because there is no clear changelog or durable maintenance/update process, and the scripts/tests claimed by README are absent from the supplied evidence.

Effectiveness6 / 15 · 2.0/5

The intended output covers tuned configuration, bottleneck classification, capacity, and remediation, and the evaluation report records a pass with some uplift. However, the report is an in-repository claim rather than inspectable execution evidence, no representative output is supplied, and operation remains environment-dependent; the static ceiling is 7 and uncertainty reduces the score.

Verifiability4 / 10 · 2.0/5

Commands, formulas, thresholds, decision rules, and an evaluation summary provide audit hooks. Evidence is still limited because no inspectable CI, test suite, or independent corroboration is supplied, and the hardware throughput figures are explicitly described as informal benchmark midpoints; therefore the score remains below the static ceiling.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Confirm authorization for automatic configuration edits and create a versioned backup for rollback.
  • Do not upload Nsight reports, RTSP endpoints, or video content to external services; the data-handling boundary is underspecified.
  • Reconcile the batch-sweep and queue-depth rules, and provide inspectable scripts, tests, CI, and maintenance/update records.
  • Verify access to the nvcr.io image, Nsight Systems, and dependencies from mainland-China environments; do not assume sudo or --privileged is acceptable.
See the full review method →

What does this skill do, and when should you use it?

This skill profiles NVIDIA DeepStream pipelines from the terminal using Nsight Systems and nvidia-smi. It establishes an inference batch plateau through an inference-only micro-benchmark, derives related pipeline settings, and then profiles the end-to-end pipeline. The report includes hardware ceilings, measured FPS, and per-plugin NVTX timings when available. It is model- and pipeline-agnostic across detection, classification, segmentation, VLM, and embedding workflows, subject to its DeepStream 9.0 environment requirements.

Reads the pipeline definition and user configuration to discover model dimensions, target FPS, and source properties; classifies pipeline elements for NVTX coverage; queries GPU, decoder, encoder, and PCIe information with nvidia-smi; sweeps inference batch sizes and records FPS; writes derived values into relevant configuration files; captures a 30-second end-to-end run with nsys profile; extracts kernel, NVTX, memory-copy, and GPU-metric reports with nsys stats; and prints a terse profile summary plus elements that were not directly instrumented.

  1. A DeepStream engineer building an efficient pipeline for a specific NVIDIA GPU.
  2. A developer measuring how many video streams can run at a target FPS.
  3. A user tuning nvinfer, nvstreammux, decoder, tracker, or queue settings.
  4. A performance engineer investigating per-plugin time in an end-to-end video pipeline.
  5. A team that needs headless, terminal-only DeepStream benchmarking with Nsight Systems.

What are this skill's strengths and limitations?

Pros
  • Uses measured inference throughput and hardware ceilings to derive settings instead of relying solely on guesswork.
  • Supports file, RTSP, USB-camera, and mixed sources without assuming a particular model, codec, or resolution.
  • Runs headlessly with nsys profile, nsys stats, and nvidia-smi.
  • Reports available per-plugin NVTX timings and explicitly identifies uninstrumented elements.
Limitations
  • The stated compatibility target is limited to DeepStream SDK 9.0, Ubuntu 22.04/24.04, and the specified NVIDIA container.
  • It does not auto-inject NVTX into uninstrumented elements.
  • It does not implement an iterative tune-measure-tune loop.
  • The supplied material gives no independent test-suite details or benchmark results for this individual skill.

How do you install this skill?

Install the skill with the repository's documented skills CLI command:

npx skills add nvidia/skills --skill deepstream-profile-pipeline --yes

To target Codex explicitly:

npx skills add nvidia/skills --skill deepstream-profile-pipeline --agent codex

The source does not document additional manual installation steps for this individual skill.

How do you use this skill?

Invoke it when creating or analyzing a DeepStream pipeline with an explicit performance request, for example: “Profile this DeepStream pipeline, measure FPS, and tune its configuration from the results.” It runs the stages in order: preset application, NVTX coverage check, hardware discovery, inference micro-benchmark, configuration derivation, and end-to-end profiling. Use the nvcr.io/nvidia/deepstream:9.0-triton-multiarch development container with nsys and nvidia-smi available on PATH.

How does this skill compare with similar options?

The repository positions deepstream-generate-pipeline as the upstream option for ordinary pipeline generation, while this skill applies when creation or analysis includes performance intent. For a newly introduced model, the source recommends using deepstream-byovm first to build the TensorRT engine, then using this profiling skill.

FAQ

Does it require a GUI?
No. It is explicitly terminal-only and uses `nsys profile` and `nsys stats` without Nsight Lens or another GUI.
Does it edit my pipeline configuration?
Yes. The instructions require reading first, then surgically writing derived values into relevant YAML, Python, or deepstream-app configuration files.
Can it measure every pipeline element?
Not necessarily. Elements without NVTX coverage are reported as not directly measurable in that build, while other diagnosis still uses micro-benchmark and hardware metrics.
What software environment is required?
The stated environment is DeepStream SDK 9.0 on Ubuntu 22.04 or 24.04, running in `nvcr.io/nvidia/deepstream:9.0-triton-multiarch`, with Nsight Systems 2024+ and `nvidia-smi` on PATH.

More skills from this repository

All from NVIDIA/skills

Automation & Ops ✓ NVIDIA · Official

RTVI-CV 2D Detection & Tracking Operations

Deploy and operate the RTVI-CV 2D video detection and tracking microservice.

Dev & Engineering ✓ NVIDIA · Official

DeepStream SOP Compliance Inference

Build and operate a GPU-accelerated service that checks industrial work-step order and SOP compliance in video.

Dev & Engineering ✓ NVIDIA · Official

DeepStream Pipeline Builder

Collects pipeline requirements interactively, then generates and validates runnable GStreamer inference pipelines for NVIDIA DeepStream.

Dev & Engineering ✓ NVIDIA · Official

NVIDIA DeepStream Development

Reliable Python pyservicemaker guidance for building NVIDIA DeepStream video analytics pipelines.

Automation & Ops ✓ NVIDIA · Official

VSS Multi-Camera 3D Detection and Tracking

Deploy multi-camera 3D perception with DeepStream and BEV Fusion.

Automation & Ops ✓ NVIDIA · Official

VSS Standalone Video Analytics API

Deploy and verify NVIDIA’s VSS video analytics REST API without the full warehouse stack.

Automation & Ops ✓ NVIDIA · Official

NeMo AutoModel Launcher Configuration

Configure NeMo AutoModel launches across local, Slurm, and cloud runs.

Automation & Ops ✓ NVIDIA · Official

VSS Video Analysis Reports

Generates structured reports from recorded video clips or incident time ranges.

Data & Analysis ✓ NVIDIA · Official

VSS Video Analytics Query

Read video-analytics incidents, metrics, alerts, and sensor data through VA-MCP.

Automation & Ops ✓ NVIDIA · Official

VSS Standalone Behavior Analytics

Deploy and operate VSS behavior analytics independently without bringing up the full warehouse stack.

Automation & Ops ✓ NVIDIA · Official

AutoMagicCalib Calibration Stack Launcher

Deploy the AutoMagicCalib microservice and web UI with Docker Compose for a ready-to-use camera calibration stack.

Dev & Engineering ✓ NVIDIA · Official

DeepStream Vision Model Importer

Automates object-detection model import, benchmarking, and reporting for NVIDIA DeepStream.

Automation & Ops ✓ NVIDIA · Official

RAG Performance Benchmark

Benchmark a deployed NVIDIA RAG Blueprint server and expose latency, throughput, and bottleneck behavior from one YAML config.

Automation & Ops ✓ NVIDIA · Official

VSS Video Summarizer

Creates timestamped narrative summaries of recorded videos through LVS, with a VLM fallback.

Dev & Engineering ✓ NVIDIA · Official

Omniverse USD Performance Tuning

Diagnose USD scene performance problems and coordinate evidence-based optimization from runtime setup through reporting.

Automation & Ops ✓ NVIDIA · Official

RT-VLM Dense Captioning Deployment

Deploy and operate NVIDIA RT-VLM to generate dense video captions and manage live streams through a REST API.

Automation & Ops ✓ NVIDIA · Official

VSS Profile Deployment Assistant

Select, deploy, verify, and troubleshoot NVIDIA VSS Compose profiles for video search and summarization.

Data & Analysis ✓ NVIDIA · Official

TAO DAFT Dataset Validator

Validate TAO DAFT dataset structure, schemas, and cross-references with tao-daft validate.

Dev & Engineering ✓ NVIDIA · Official

DALI Dynamic Mode Assistant

Helps agents write, review, and migrate NVIDIA DALI imperative dynamic-mode code.

Dev & Engineering ✓ NVIDIA · Official

DOCA Debug

A cross-library diagnostic guide for NVIDIA DOCA build, link, runtime, and program failures.

Related skills