NVIDIA Corporation

Deploy and operate the DOCA UROM Service container on BlueField Arm. Configure communication settings, check host pairing and version compatibility, and investigate slow or incomplete remote memory operations submitted by the host.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying the service container on BlueField Arm
• Checking host pairing and compatible versions
• Investigating slow collective communication

Create a new data source wrapper, code that connects remote weather data to Earth2Studio. The skill covers source selection, variable mapping, implementation, tests, and validation with real data, with further steps for documentation and pull request submission.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect a new remote data store to Earth2Studio
• Add support for gridded forecasts or station observations
• Map remote variable names to Earth2Studio names

Read hardware counters, values describing device activity, from BlueField or ConnectX in a DOCA application. The skill guides supported-counter checks, reader setup, sampling, and error handling across six domains, including PCC, DPA, PHY, and PCI.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading PCC counters from a BlueField application
• Sampling DPA counters
• Adding PHY or PCI counter reads to an application

Open a completed LeRobot dataset in a browser to inspect camera videos, state and action timelines, and episode details. The skill manages a local server and reports observations together with the command to stop it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect the latest converted LeRobot dataset
• Check that every camera video plays
• Review state and action timelines

Diagnose failed Dynamo deployments using Kubernetes status, events, and logs. Gather evidence without changing the cluster, identify the likely failure layer, and return a specific command or patch to try next.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate pods that fail to start
• Diagnose model download and storage failures
• Check frontend, router, and API health

Run an Isaac for Healthcare workflow from robot recordings through dataset preparation, policy training, and checkpoint validation. Uses the maintained pipeline driver, checks the planned commands first, and verifies artifacts and logs at each stage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running the full recording-to-validation pipeline
• Checking planned stages and artifact paths before execution
• Reviewing datasets, training logs, and checkpoints

Set up or repair the FoundationPose perception pipeline and build FoundationStereo TensorRT engines for depth estimation. It checks system requirements, resolves dependency and CUDA library issues, and verifies engines against the intended scene dimensions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Install the pipeline on a supported GPU machine
• Resolve SAM3 and TAO dependency conflicts
• Diagnose missing CUDA runtime libraries

Record human-operated robot demonstrations in workflow HDF5 files, a structured data format. The skill guides supported input-device selection, foreground recording, and checks of robot motion, camera observations, saved episodes, and task outcomes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording keyboard-controlled robot demonstrations
• Recording demonstrations with supported leader or VR devices
• Checking saved actions and camera observations

Check whether a Dynamo deployment is ready for disaggregated serving, where input processing and token generation run separately. Read-only probes inspect transport settings, GPU networking capabilities, and NIXL transfer-test readiness, then report gaps and next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check communication readiness after deployment
• Inspect transport setup before benchmarking
• Investigate suspected communication bottlenecks

Find and run Holoscan Sensor Bridge example applications that match a connected development kit, board, software version, and sensors. Monitor timed runs, investigate failures, suggest code or environment changes, and summarize the session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find example apps compatible with connected sensors
• Run a sample application for 60 seconds
• Analyze failures and retry an application

Select an existing NVIDIA Dynamo Kubernetes deployment recipe for a model, inference framework, and GPU setup. The skill validates requirements, patches necessary settings, deploys the recipe, and checks the endpoint with an OpenAI-compatible test request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find an existing deployment recipe for a model and GPU setup
• Validate storage, images, and token secrets before deployment
• Deploy a Dynamo recipe and run a basic API check

Investigate missing DOCA telemetry metrics with doca_telemetry_utils. Discover diagnostic counters, translate counter names to Data IDs and back, and check device support before adding counters to an exporter configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating metrics missing from a collector
• Checking which counters a BlueField device supports
• Translating logged Data IDs into counter names

Assess whether a DOCA application needs low-level communication controls beyond its higher-level APIs. For those cases, guide queue configuration, libibverbs migration, and error diagnosis using installed headers, version checks, and device capability queries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Decide whether higher-level DOCA APIs are sufficient
• Configure a queue attribute unavailable through the task API
• Port libibverbs code into DOCA Core

Fine-tune GR00T or openpi robot policies using compatible LeRobot data. Check dataset requirements, preview the training configuration, run training, and verify that a saved checkpoint, a file containing the trained model, loads through the inference backend.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tuning a robot policy on LeRobot data
• Checking dataset compatibility before training
• Training with specified steps, batch size, and GPU count

Set up Earth2Studio with uv or pip using commands matched to your environment and planned models. The skill guides optional dependency selection, cache configuration, installation checks, and dependency troubleshooting while leaving package installation to the user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Install Earth2Studio in a new or existing Python project
• Identify optional packages for planned models
• Configure cache locations and download timeouts

Grade recorded workflow episodes against a written success criterion using a vision model, which interprets sampled camera images. Summarize pass and fail counts, or optionally extract successful episodes into a separate HDF5 dataset.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Label recorded episodes against a written success criterion
• Extract successful episodes into a separate dataset
• Check sampled camera frames before sending images

Check installed DOCA versions across package metadata, application files, runtime tools, and BlueField system information. Use the results to investigate build and runtime mismatches, check feature availability, and understand NGC container version tags.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether installed DOCA versions agree
• Investigate build and runtime version mismatches
• Check feature support for a specific release

Check whether a requested Holoscan SDK 5.x release supports Conda installation. When packages are unavailable or unconfirmed, find an alternative installation method that preserves the requested SDK version and C++ or Python requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check Conda support for Holoscan SDK 5.x
• Choose an alternative way to install SDK 5.0
• Find an installation method for C++ or Python

Run quality assurance tests on Holoscan Sensor Bridge hardware from a supplied test document. Select tests that match the connected equipment, execute automatable cases, evaluate pass or fail, and produce a structured results report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run a documented test plan on an HSB board
• Select automated tests for the connected sensors
• Investigate failed tests using execution logs

Investigate DOCA build failures, runtime errors, and silent tools by checking each system layer. Get guidance on increasing log detail and collecting reproducible evidence for troubleshooting or a Developer Forum question.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Identify the layer behind a DOCA build or runtime failure
• Increase log detail for a silent DOCA tool
• Collect reproducible evidence for a forum question

Prepare an environment for evaluating speech recognition on clinical terms. Checks the API key and Python dependencies, then tests NVIDIA's hosted services by generating speech from one synthetic sentence and transcribing it before the next stage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a clinical speech recognition evaluation
• Checking API access from a fresh environment
• Testing speech synthesis and transcription together

Measure how quickly a host or DPU CPU installs and deletes DOCA Flow rules. Choose a JSON workload and backend, run repeated benchmarks, and record hardware, software, and execution settings so results can be assessed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measure BlueField rule installation rates
• Compare DPDK and DOCA backends
• Investigate differences from published benchmark results

Build and debug the shared foundations of DOCA applications on BlueField or ConnectX hardware. Get guidance on device capabilities, memory buffers, context lifecycles, task completion processing, and separate logging controls for the SDK and application.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up the foundations of a DOCA application
• Investigating tasks that submit but never complete
• Sharing memory buffers across DOCA libraries

Connect existing DOCA Flow processing rules and resources to BlueField’s DPA processor. The skill guides export sequencing, operation queues, counter access, and entry or memory updates, and helps diagnose failures between host setup and device-side access.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Expose an existing DOCA Flow pipe to a DPA kernel
• Investigate exported entries that the kernel cannot see
• Check queues for counter access and entry updates