speculative-decodingTrain, debug, and validate a speculative decoding draft model (EAGLE3, DFlash, DSpark, Domino) through the ModelOpt launcher pipeline. Use when the user wants to add a new model to a draft-training pipeline, asks why a pipeline run failed, wants experiment…qadRun explicitly requested ModelOpt Quantization-Aware Distillation (QAD) through Megatron Bridge (recommended) or Hugging Face Transformers to recover a measured BF16-to-PTQ accuracy gap. Use only when the user explicitly asks for QAD, including its topology,…evaluationEvaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "run nel". Handles deployment, config generation, and evaluation execution.…monitorMonitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation", "what's the status of the PTQ", "check on job" followed by a SLURM job ID, or after any skill submits…compare-resultsEstablish baseline-vs-candidate evaluation plans, delegate missing evaluations, compare validated results, and decide quantization feasibility. Use when the user asks to compare baseline vs quantized runs, explain an accuracy drop/regression, verify whether a…run-agentxRun the AgentX agentic serving benchmark with the SemiAnalysis harness. Use for AgentX setup, dataset downloads, concurrency sweeps, or serving latency and throughput comparisons.ptqUse when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace…release-cherry-pickAudit merged bug-fix PRs and release NVBugs for missing cherry-pick labels, then cherry-pick labeled PRs into a release branch and open a PR. Use when asked to "cherry-pick PRs for release/X.Y.Z", "pick PRs to release branch", "verify cherry-pick labels", or…
Repository-Explorer
NVIDIA · Repositories und repräsentative Skills - Seite 2
Repository-Ansicht von 1.199 gesammelten Skills in 113 GitHub-Repositories.
dgx-stationInspect and guide NVIDIA DGX Station GB300 development using the local dgx-assist CLI and pinned NVIDIA playbooks. Use for general Station platform questions, Software 1.0 or 2.0 compatibility, GB300 or RTX GPU selection, UUID ordering, mixed ATS/HMM…dgx-station-diagnoseRun and interpret the complete read-only dgx-assist diagnostic suite for NVIDIA DGX Station GB300, correlate findings with pinned NVIDIA playbooks, export a redacted support bundle, and apply one separately approved allowlisted fix. Use when the user reports…dgx-station-inferenceResolve, tune, preflight, launch, verify, inspect, and stop exact-model inference on NVIDIA DGX Station through dgx-assist. Use for vLLM or SGLang container selection, NGC versus upstream, GPU memory utilization, CPU or KV offload, HBM fit, KV-cache sizing,…dgx-station-migInspect NVIDIA DGX Station GB300 MIG state and installed-driver profiles, create a digest-bound layout plan, disclose disruption and restoration, and apply an approved still-valid plan. Use when the user asks to enable, disable, partition, reconfigure,…analysis-methodsTeaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.case-summaryPrepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.clinical-delegationHow to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.clinical-knowledgeTeaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal values and identify care gaps.
nightly-syncDomain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues. Use when working on the nightly sync PR; investigating a nightly sync failure; resolving merge conflicts between main…mcore-build-and-dependencyContainer-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and updating uv.lock. Use when adding, removing, or updating a dependency; editing pyproject.toml or…mcore-bump-base-imageBump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker/.ngc_version.dev` and GitLab CI in `.gitlab/stages/01.build.yml`), the post-bump CI loop (re-run functional tests,…mcore-cicdCI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a pull-request/BRANCH ref — always dry-run and verify the destination first; never run against shared or…mcore-create-issueInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure. Use when user shares a GitHub Actions URL and wants to file a bug report; 'create an issue for this failure', 'file a bug for this CI run', 'triage this GitHub Actions…mcore-linting-and-formattingLinting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules. Use when running linting or autoformat; fixing style violations before a PR; 'pre-commit fails', 'ruff error', 'isort',…mcore-migrate-gpt-to-hybridMigration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel, including the mechanical steps for transferring an existing pretrain_gpt.py launch script. Use when migrating or reviewing a…mcore-onboard-gb200-1node-testsOnboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests. Use when adding GB200 github-mr tests; creating single-node variants of existing tests; expanding CI coverage for GB200; 'add GB200 MR tests', 'onboard GB200 1-node',…
nvalchemi-model-wrappingHow to wrap an arbitrary MLIP (Machine Learning Interatomic Potential) using the BaseModelMixin interface to standardize inputs, outputs, and embeddings. Use when integrating a model such as MACE or AIMNet2 (e.g. MACEWrapper, loading pretrained checkpoints)…nvalchemi-distributedHow to run domain-decomposed (multi-GPU) MLIP simulations with DomainParallel — choose between the halo and graph-partition strategies, author a distribution_spec so a bring-your-own model runs under domain decomposition, and write a custom dynamics…nvalchemi-dynamics-apiHow to configure and run dynamics simulations, compose multi-stage pipelines (FusedStage, DistributedPipeline), use inflight batching, and manage data sinks. Use when writing any simulation script — molecular dynamics (NVE/NVT), structure relaxation or…nvalchemi-distillationHow to distill a large teacher MLIP into a small student with DistillationStrategy — teacher signals and offline dataset labeling, the teacher_* loss targets, the on-policy segment loop (propagator, replay buffer, mixed loader), checkpoints and restart, and…nvalchemi-dynamics-hooksHow to use and write dynamics hooks — callbacks that observe or modify batch state at specific points during each simulation step. Use when a simulation needs neighbor-list rebuilds, convergence checks or early stopping, temperature control, per-step logging…nvalchemi-data-structuresHow to use AtomicData and Batch, the core graph-based data structures for representing atomic systems and batching them for GPU computation. Use when building systems from positions, cells, and atomic numbers, converting from ASE Atoms, batching or unbatching…nvalchemi-mepHow to compute minimum-energy paths (MEPs) and transition-state estimates with nvalchemi.dynamics.mep: building initial paths (interpolation, alignment, IDPP) and running batched nudged elastic band (NEB) with the NEB strategy or by building it manually with…nvalchemi-reportingHow to add observability to nvalchemi dynamics and training workflows using ReportingOrchestrator, RichReporter, TensorBoardReporter, scalar extraction, custom reporter callbacks, and dynamics LoggingHook. Use when showing live progress, writing TensorBoard…
kit-app-streaming-debugUse when investigating Kit app livestream performance bottlenecks, WebRTC/native StreamSDK lag, freezes, dropped frames, browser WebRTC stats, copy fence timeouts, NVST_R_BUSY, disconnects, or resolution mismatch warnings in omni.kit.livestream.nvtx-pythonProfile Python functions with NVTX in non-Kit environments (Isaac Lab 3.0+ standalone, any Python app without Carbonite). Uses a bundled PYTHONPATH-scoped sitecustomize.py with sys.setprofile hook, NVTX push/pop ranges, module include/exclude filtering, and…perf-tuningResolve common Kit/Isaac Sim/Isaac Lab performance issues using specific settings and configuration changes. Covers PresentFrame stalls, resolveSamplerFeedback, headless mode, multi-GPU tradeoffs, DLSS/DLSS-G, PhysX tuning, RTX presets…install-profilersInstall profiling tools for Isaac Sim / Isaac Lab / Kit-based applications. Covers Nsight Systems (`nsys` CLI), `sqlite3`, Tracy `csvexport`, canonical Tracy `capture`/`capture-release`, and `update` for memory strip tests, with optional…nsys-analyzeAnalyze profiling data from Kit-based apps. Covers Omniverse-specific NVTX zone interpretation, phase detection using sqlite3, Tracy Statistics/Range Limit analysis, csvexport fallback queries, and two-version comparison methodology. Use after capturing…profiling-apiAdd profiling zones, metrics, and annotations to Kit-based C++ and Python code. Covers Carbonite macros (CARB_PROFILE_ZONE, CARB_PROFILE_FUNCTION, GPU zones), Python profiler API (decorators, begin/end), profiler masks, channels, Tracy plot data, event…profilingCapture performance traces using CPU ChromeTrace, Tracy, and Nsight Systems/NVTX for Kit-based applications (Isaac Sim, Isaac Lab, Kit SDK). Covers COLD/WARM/TRACY measurement separation, canonical Tracy capture sequence, last-resort force-kill handling, nsys…tracy-memoryProfile CPU and GPU memory allocations using Tracy in Kit-based applications after Tracy capture tooling is installed. Covers LD_PRELOAD setup for liballocwrapper.so, Kit memory-channel flags, capture binary isolation (unset LD_PRELOAD), tracy-update…
optimize-model-precisionEvaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.profile-modelMeasure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.review-trtmc-prReview a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, third-party dependency and license obligations, and exact-head validation…pr-babysitterUse when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.debug-trt-mismatchDiagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.doc-syncAudit and update TensorRT-Model-Connect documentation when code, public APIs, family ownership, commands, or model support have changed.fp16-trt-networkImplement or review FP16 and BF16 behavior in one family-owned, strongly typed TensorRT network without changing unrelated families.setup-trtmc-environmentPrepare a TensorRT-Model-Connect development or validation environment from a fresh checkout on a host without a known working setup.
nat-evaluationUse when designing, configuring, running, or troubleshooting NeMo Agent Toolkit evaluations, datasets, evaluator selection, ATIF surfaces, quality gates, custom evaluators, and `nat eval`.nat-optimizationUse when configuring or running NeMo Agent Toolkit optimization with `nat optimize`, including Optuna parameter tuning, prompt evolution, optimizer sizing, output interpretation, and optimizer datasets.nat-workflow-creationUse when creating, editing, validating, running, or troubleshooting NeMo Agent Toolkit workflow YAML, component discovery, LLM configuration, and common `nat` CLI commands.nat-user-rulesUse first for general NVIDIA NeMo Agent Toolkit coding-agent behavior, task routing, naming conventions, component discovery rules, and cross-skill guidance.nat-telemetryUse when adding, configuring, or troubleshooting NeMo Agent Toolkit logging, tracing, telemetry exporters, OpenTelemetry, Langfuse, LangSmith, Weave, Phoenix, profiling, or observability provider integrations.skill-evolutionUse before creating, editing, or deciding whether to update any AI coding agent skill in this repository, including corrections to existing skill behavior, references, or routing.nat-agent-configurationUse when selecting, configuring, composing, or troubleshooting NeMo Agent Toolkit agents and control-flow components, including ReAct, tool-calling, ReWOO, reasoning, router, sequential, parallel, and sub-agent patterns.nat-installationUse when installing or configuring NVIDIA NeMo Agent Toolkit, verifying the `nat` CLI, setting up optional extras, or creating a first hello-world workflow.
nvflare-convert-huggingfaceConvert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation, and job export; use when the user names Hugging Face or preliminary source inspection identifies one…nvflare-convert-lightningConvert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use only when the request names federated/NVFLARE conversion or asks multiple sites to train collaboratively…nvflare-sharedInternal NVFLARE conversion references and templates. Use only when another NVFLARE skill directs you to a shared workflow, policy, or asset.nvflare-autoflUse for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production. Do not use for code conversion, diagnosis-only work, or deployment setup.nvflare-convert-pytorchConvert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use when the user names plain PyTorch or preliminary source inspection identifies one plain-PyTorch owner,…nvflare-diagnose-jobUse when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXECUTION_EXCEPTION, or produced suspicious errors. Diagnose in simulation, POC, or production by collecting bounded…nvflare-fed-statsCompute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count, failure_count, pixel-intensity histogram) across NVFLARE sites via FedStatsRecipe — automatic and…nvflare-orientRoute open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership; never load this skill merely to inspect a concrete conversion request before selecting its detected framework…
nvca-self-managed-installInstall or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.nvca-values-customizationCustomize NVCA Operator Helm chart values in the native monorepo. Use when modifying vendored defaults, changing stack-derived install values, adding deployment-time overrides, or updating scripts under deploy/helm/nvca-operator.nvcf-explore-stackNavigate and explain the NVCF self-hosted stack inside the monorepo. Maps helmfile releases to their charts, image-source subtrees, helm hooks, namespaces, and `needs:` dependency chains. Reads deploy/stacks/self-managed/helmfile.d/*.yaml.gotmpl and…nvcf-self-managed-cliInstall, operate, and tear down self-hosted NVIDIA Cloud Functions (NVCF) deployments with nvcf-cli. Use for control-plane or compute-plane install, status checks, cluster registration, function deploy/invoke, task create/list/cancel/delete, API keys, admin…nvcf-self-managed-installationInstall and operate NVCF self-hosted control-plane and separate compute-plane stacks. Covers Helmfile values and CLI profile installation flows, teardown, values overrides, pull secrets, and troubleshooting. Use for nvcf-self-managed-stack,…add-featureAdd a new UI feature to the nvcf-ui app — folder structure, routing, data loading, lazy-loading, testing, and completion checklist. Use when creating a new feature folder, adding a page or view, wiring routes, building a new screen, or deciding whether to…codegenRun and manage the Orval code generation pipeline for API hooks, TypeScript models, and MSW mocks. Use when editing an OpenAPI spec, running task generate, adding or modifying MSW scenarios, troubleshooting generated code, or when generated hooks are missing…runStart the nvcf-ui development server. Use when asked to run, start, or launch the app, or to verify a change works in the browser.
k8s-launch-kit-configUse this skill when the user needs help understanding, creating, or editing a k8s-launch-kit (l8k) configuration file (l8k-config.yaml or cluster-config.yaml). Activate for: config file questions, parameter tuning, subnet configuration, NV-IPAM setup, DOCA…k8s-launch-kit-deployUse this skill when the user wants to deploy generated NVIDIA networking manifests to a Kubernetes cluster using k8s-launch-kit (l8k). Activate for: applying manifests, deploying to cluster, the `l8k deploy` subcommand or the legacy --deploy flag on `l8k…k8s-launch-kit-generateUse this skill when the user wants to generate Kubernetes YAML manifests for NVIDIA networking deployment using k8s-launch-kit (l8k). Activate for: manifest generation, profile selection, choosing between…k8s-launch-kit-validateUse this skill when the user wants to verify that an NVIDIA networking deployment matches the configuration that produced it. Activate for: 'is my deployment correct', 'are all the manifests applied', 'does the network operator version match', 'verify…k8s-launch-kit-discoverUse this skill when the user wants to discover their Kubernetes cluster's network hardware capabilities using k8s-launch-kit (l8k). Activate for: cluster discovery, hardware detection, NIC detection, finding what GPUs or NICs are in a cluster, creating a…k8s-network-engineerEmbody a senior NVIDIA Networking Engineer who is an expert on deploying cloud-native networking on Kubernetes with k8s-launch-kit (l8k). Activate whenever the user mentions NVIDIA network profiles, SR-IOV, RDMA, Spectrum-X, BlueField, ConnectX, NIC…k8s-launch-kit-cleanRemove an NVIDIA Network Operator deployment from a Kubernetes cluster with l8k clean. Use when the user explicitly asks to uninstall, tear down, remove, reset, or clean a Network Operator installation, delete its custom resources, or keep the Helm chart…k8s-launch-kit-pipelineUse this skill when the user wants to run the full k8s-launch-kit (l8k) pipeline end-to-end: discover cluster hardware, select a profile, generate manifests, and deploy them all in one command. Also activate for CI/CD integration, automation pipelines,…
accelerated-computing-cudfOfficial 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.reproduce-ciReproduce cudf CI failures locally. Provide a GitHub Actions job URL to auto-discover parameters, or supply the container image and CI script directly.cudf-query-engine-builderBuilds a native cuDF proof of concept for a query engine with no working GPU path. Use when an engineer supplies target-engine or adapter code plus a query, operator sequence, or CPU implementation selected for the POC and needs working libcudf C++ or cuDF…review-cudfUse this skill to review GitHub pull requests for cudfdebug-cudf-pandasDebug and fix pandas test suite failures under the cudf.pandas compatibility layer. Use when given pytest node IDs of failing pandas tests that need to be fixed for cudf.pandas compatibility.perf-compare-cudfBenchmark a cuDF branch, WIP changes, or a PR against the `main` branchbuild-test-cudf-javaBuild and test cudf Java bindings (cudf-java) inside a cudf devcontainer. Use when the user asks to build, compile, or test Java code in the cudf repository.update-narwhals-testingUse when updating Narwhals for cudf-polars and cudf testing in CI
integrate-a-modelEnd-to-end workflow for porting an external video diffusion model into a flashdreams integration — scope the architecture, scaffold a workspace-member plugin, reuse an existing recipe, write the checkpoint key-remap, layer model-specific conditioners, wire…maintaining-oss-stateMaintain FlashDreams's OSS-release state — the LICENSE / NOTICE / THIRD-PARTY-NOTICES / REUSE.toml / LICENSES/ / CONTRIBUTING.md collateral that satisfies OSRB Bug 6107043, the per-file SPDX headers, the third-party dependency manifest in THIRD-PARTY-NOTICES,…python-docstring-styleWrite Python docstrings and inline comments matching the flashdreams house style — SPDX header, one-line module docstring, Google-style function docstrings (Args/Returns/Raises), PEP 257 attribute docstrings on dataclass/class fields *and on module-level…security-code-reviewReview FlashDreams changes for production, policy, and security risk. Use for security-sensitive changes, release-critical paths, or final merge approval.flashdreams-preparationUse when changing FlashDreams V2 downloads, compilation, native loading, model construction, runtime validation, or application preloading.flashdreams-postprocessingAdd or modify FlashDreams video post-processing processors, sessions, presets, and runner stream wiring. Use when implementing a new VideoPostProcessorConfig / VideoPostProcessor / VideoPostProcessorSession, registering a --postprocess.preset entry point,…flashdreams-integrationsNavigate the FlashDreams package layout and integration architecture: core vs infra vs recipes vs workspace integrations, Transformer/Encoder/StreamingDecoder/Pipeline config contracts, AR caches, CP, CFG, KV cache, CUDA graph wrapping, runner registration,…apply-inference-optimizationsApply FlashDreams-style inference speedups to model integrations after a baseline exists: bounded windows and fixed K/V caches, cache/decode overlap, `torch.compile`, CUDA graph capture, attention backend checks, decoder layout or replacement,…