GPU, CUDA, and accelerated-computing skills from NVIDIA.
Official NVIDIA-verified catalog of product skills mirrored from NVIDIA product repositories.
Arranged in the author's recommended order. Walk through them in sequence, or open any one on its own.
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA cuOpt.
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
LP, MILP, QP – concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
Vehicle routing (VRP, TSP, PDP) with cuOpt – Python API only.
Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched).
Install and verify cuPyNumeric for Python – requirements, commands, verification. Source builds are out of scope.
Pre-migration readiness assessor for porting NumPy to cuPyNumeric.
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants.
DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd).
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API.
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.
Stage 1 of Clinical ASR Flywheel.
Stage 2 of the Clinical ASR Flywheel.
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic).
Stage 4 of the Clinical ASR Flywheel.
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink.
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes.
Start or patch Dynamo router modes and run router endpoint smoke checks.
Diagnose failed or unhealthy Dynamo deployments.
Fetch weather/climate data via Earth2Studio data sources for specific variables and times.
Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference).
Find Earth2Studio models, data sources, and examples for a weather/climate use case.
Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment.
Install Holoscan SDK via the NGC Docker container.
Install Holoscan SDK natively on Ubuntu via apt.
Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2.
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510).
Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests can run automatically, executes them with pass/fail evaluation.
Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence.
Used for header-only preflight of one DICOM series folder before conversion or inference.
Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence.
Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests.
NVIDIA RAG Blueprint – deploy, configure, troubleshoot, and manage.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality).
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config.