- Nemoclaw Contributor Create PrCreate GitHub pull requests that follow the NemoClaw PR template, then monitor CI and automated review feedback. Use when the user wants to create a new PR, submit code for review, open a pull request, or push changes for review. Trigger keywords - create PR, pull request, new PR, submit for review, open PR, push for review.NVIDIA/NemoClaw21,581
- Nemoclaw Contributor OnboardPrepare a NemoClaw source checkout for compliant contribution through the repository's one-command setup and readiness doctor. Use when a new contributor asks to set up a development machine, prepare a checkout for a first PR, repair local contributor tooling, verify contributor readiness, launch the pinned coding agent, or decide whether optional runtime onboarding is needed. Trigger keywords - contributor setup, developer onboarding, first PR, dev setup, dev doctor, repair checkout, prepare deNVIDIA/NemoClaw21,581
- Nemoclaw Contributor Onboard Messaging ChannelGuide NemoClaw contributors through adding or reviewing a new messaging channel in the manifest-first messaging architecture. Use when onboarding a channel for OpenClaw, Hermes, or both; mapping upstream channel docs and source code into NemoClaw manifests; confirming credentials, plugin/package installs, reachability checks, network policy presets, docs, and tests. Trigger keywords - add messaging channel, onboard messaging channel, new channel, messaging integration, channel manifest, OpenClawNVIDIA/NemoClaw21,581
- Nemoclaw Contributor Update DocsScan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages for release prep. Use when docs have fallen behind code changes, after a batch of features lands, during daily release prep, before cutting a release tag, or when recovering missed post-release docs. Trigger keywords - update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift, release prep docs, pre-tag docs, release note dNVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Cross Issue SweepScans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line evidence. Use when reviewing a PR to discover bundling opportunities or downstream impact across the issue queue.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Cut Release TagCreates deterministic NemoClaw semver release tags on origin/main, handles release housekeeping, and drafts release notes. Use when cutting a release, tagging a version, shipping a build, creating vX.Y.Z tags, or preparing release announcements.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer DayRuns the daytime maintainer loop for NemoClaw, prioritizing items labeled with the current version target. Picks the highest-value item, executes the right workflow (merge gate, salvage, security sweep, test gaps, hotspot cooling, or sequencing), and reports progress. Use during the workday to land PRs and close issues. Designed for /loop (e.g. /loop 10m /nemoclaw-maintainer-day). Trigger keywords - maintainer day, work on PRs, land PRs, make progress, what's next, keep going, maintainer loop.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer EveningRuns the end-of-day maintainer handoff for NemoClaw. Checks version target progress, records stragglers for an automatic post-tag bump, generates a QA handoff summary, and cuts the release tag. Use at the end of the workday. Trigger keywords - evening, end of day, EOD, wrap up, ship it, cut tag, handoff, done for the day.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Find Review PrFinds open security-labeled GitHub PRs with Urgent or High Project Priority, links each to its issue, detects duplicates, and presents a table of review candidates. Use when looking for the next PR to review. Trigger keywords - find pr, find review, next pr, pr to review, duplicate pr, security pr.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer MorningRuns the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and outputs the daily plan. Use at the start of the workday. Trigger keywords - morning, standup, start of day, daily plan, what are we shipping today.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Normalize Title TagsNormalizes GitHub issue and PR titles by removing any bracketed [NemoClaw] tag case-insensitively, even when the tag appears later in the title. Use when cleaning issue tags, bulk-renaming titles, or normalizing repo title hygiene.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer PoliciesRead-only maintainer policy reference for NemoClaw agents, engineers, and maintainers. Use when answering NemoClaw project-management workflow questions, including GitHub Issue Type, labels, Project fields, daily release labels, triage, duplicates, blocked items, and maintainer workflow decisions. Trigger keywords - maintainer policy, workflow policy, project workflow, issue type, labels, label taxonomy, needs labels, project status, blocked issue, duplicate issue, daily release label, release tNVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Pr ComparatorCompares competing PRs that target the same issue and recommends which one to merge. Runs gate, correctness, and quality checks; outputs a deterministic scorecard with reasoning trace. Use when an issue has two or more open PRs and a maintainer needs to decide which to merge.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Release NotesDrafts NemoClaw release notes from live GitHub tag and compare data. Produces the repo's narrative release-note style with three lead paragraphs, categorized shipped changes, why-it-matters bullets, and external-only contributor thanks. Use after cutting a release tag or when asked to draft release notes, prepare an announcement, write a changelog, or summarize v0.0.x.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Security Code ReviewPerforms a comprehensive security review of code changes in a GitHub PR or issue. Checks out the branch, analyzes changed files against a 9-category security checklist, and produces PASS/WARNING/FAIL verdicts. Use when reviewing pull requests for security vulnerabilities, hardcoded secrets, injection flaws, auth bypasses, or insecure configurations. Trigger keywords - security review, code review, appsec, vulnerability assessment, security audit, review PR security.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer TriageAI-assisted triage for NVIDIA/NemoClaw issues and PRs using native Issue Type, Project fields, and the canonical label taxonomy. Supports single-item and batch modes, presents a dry run, and applies only the accepted write set. Trigger keywords - triage, label issues, suggest labels, batch triage, triage issue, triage PR, label this, what labels.NVIDIA/NemoClaw21,581
- Nemoclaw Maintainer Verify StaleVerifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the latest tag. Use when maintainers ask to verify stale issues, reproduce old bugs on latest, or drain the bug backlog. Uses native Issue Type, canonical labels, local/Brev reproduction, by-design detection, confidence scoring, approved Project updates, and redacted verdict comments; never auto-closes.NVIDIA/NemoClaw21,581
- Nemoclaw Skills GuideStart here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what can I do, help, guide, index, overview, start here.NVIDIA/NemoClaw21,581
- Nemoclaw User GuideGuides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.NVIDIA/NemoClaw21,581
- Nemoclaw User GuideGuides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.NVIDIA/NemoClaw21,581
- 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.NVIDIA/Megatron-LM16,943
- 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, refresh golden values, mark broken tests), and the gotchas that bit PRsNVIDIA/Megatron-LM16,943
- 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 protected branches), and CI failure investigation.NVIDIA/Megatron-LM16,943
- Mcore Create IssueInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure.NVIDIA/Megatron-LM16,943
- Mcore Linting And FormattingLinting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.NVIDIA/Megatron-LM16,943
- Mcore Onboard Gb200 1node TestsOnboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.NVIDIA/Megatron-LM16,943
- Mcore Run On SlurmHow to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.NVIDIA/Megatron-LM16,943
- Mcore Split PrSplit a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.NVIDIA/Megatron-LM16,943
- Mcore TestingTest system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.NVIDIA/Megatron-LM16,943
- Nightly SyncDomain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.NVIDIA/Megatron-LM16,943
- Respond To IssueResearch and draft a response to a GitHub issue or question from an external contributor.NVIDIA/Megatron-LM16,943
- Update Golden ValuesRefresh golden values from a GitHub Actions workflow run (failing-only or all jobs), score the change with average normalized relative differences, and produce a PR-ready summary. Use when the user asks to update goldens for a CI run, refresh golden values from a workflow ID, or generate a golden-value diff summary for a PR description.NVIDIA/Megatron-LM16,943
- Ad Accuracy DebugDebug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference and the root cause is unknown.NVIDIA/TensorRT-LLM14,022
- Ad Add Fusion TransformationClaude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.NVIDIA/TensorRT-LLM14,022
- Ad Conf CheckCheck whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR). Use when the user wants to verify config application, debug config issues, or check if AutoDeploy transforms (piecewise CUDA graph, multi-stream, sharding, fusion, etc.) were applied or fell back. Triggers on: "check config", "verify config", "ad-conf-check", "were my configs applied", "config not working", "check if piecewise is enabled", "check log for config", NVIDIA/TensorRT-LLM14,022
- Ad Graph DumpEnable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR. Use when you need before/after graphs per transform, to locate subgraphs, or to confirm a rewrite ran. Paths and behavior are grounded in tensorrt_llm/_torch/auto_deploy (GraphWriter, BaseTransform). Complements ad-add-fusion-transformation.NVIDIA/TensorRT-LLM14,022
- Ad Layer VisualizerVisualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram. Optionally annotate nodes with actual GPU kernel names and durations from an nsys trace. Use when the user wants to visualize, inspect, or debug a layer in an AutoDeploy model graph dump. Triggers on: "visualize layer", "show layer", "graph of layer", "layer visualization", "dump graph layer". Assumes graph dumps already exist in a directory (produced by AD_DUMP_GRAPHS_DIR).NVIDIA/TensorRT-LLM14,022
- Ad Model OnboardTranslates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.NVIDIA/TensorRT-LLM14,022
- Ad Model OnboardTranslates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.NVIDIA/TensorRT-LLM14,022
- Ad Sharding Ir PortAdds sharding-aware IR hints (op substitutions, sharding kwargs, all_reduce insertions) directly into an existing AutoDeploy custom model (modeling_*.py). Edits the file in place — no separate _ir.py copy. Validates with apply_sharding_hints and end-to-end multi-GPU runs.NVIDIA/TensorRT-LLM14,022
- Exec Local CompileCompile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.NVIDIA/TensorRT-LLM14,022
- Exec Slurm CompileCompile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.NVIDIA/TensorRT-LLM14,022
- Kernel Cute WritingWrite and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework NVIDIA/TensorRT-LLM14,022
- Kernel Tileir OptimizationOptimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates vNVIDIA/TensorRT-LLM14,022
- Kernel Triton WritingONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).NVIDIA/TensorRT-LLM14,022
- Perf AnalysisPerformance analysis coordination workflow. Guides profiling delegation, bottleneck classification (compute/memory/launch/communication/sync), and structured report generation. Use when the user asks to analyze performance, profile a workload, check MFU/SOL, or diagnose bottlenecks.NVIDIA/TensorRT-LLM14,022
- Perf Host AnalysisAnalyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-aNVIDIA/TensorRT-LLM14,022
- Perf Host OptimizationProfiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.NVIDIA/TensorRT-LLM14,022
- Perf Nsight Compute AnalysisAnalyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis, metric interpretation, and programmatic .ncu-rep report analysis. NOT for kernel writing or code generation, Nsight Systems (nsys), host-side profiling, or system-level profiling.NVIDIA/TensorRT-LLM14,022
- Perf Nsight SystemsNsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, or profile distributed training with NCCL overlap analysis. NOT for kernel-level metrics like SOL%, occupancy, or roofline (use perf-nsight-compute-analysis for ncu). NOT for writing or generating kernels. NOT for applying optimizations like CUDA Graphs.NVIDIA/TensorRT-LLM14,022
- Perf OptimizationPerformance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.NVIDIA/TensorRT-LLM14,022
- Perf Torch Cuda GraphsApply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.NVIDIA/TensorRT-LLM14,022
- Perf Torch Sync FreeIdentify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies false vs true dependencies, provides sync-free alternatives. Triggers: sync-free, synchronization, .item(), .cpu(), host-device sync, eliminate syncs, CPU stall, non_blocking, set_sync_debug_mode, cudaStreamSynchronize, cudaEventSynchronize, remove syncs, async GPU.NVIDIA/TensorRT-LLM14,022
- Perf Workload ProfilingCode instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying oNVIDIA/TensorRT-LLM14,022
- Trtllm Code ContributionBest practices for contributing code to TensorRT-LLM. Covers the official contribution process (issue tracking, fork workflow, DCO signing), coding guidelines, implementation workflow, common mistakes, testing strategy, commit hygiene, and review readiness. Incorporates rules from CONTRIBUTING.md and CODING_GUIDELINES.md plus lessons distilled from real PR retrospectives. Use when implementing new features, optimizations, or bug fixes in the TensorRT-LLM codebase.NVIDIA/TensorRT-LLM14,022
- Trtllm Codebase ExplorationSystematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.NVIDIA/TensorRT-LLM14,022
- Trtllm Flashinfer UpgradeUpgrade flashinfer-python version in TensorRT-LLM. Fetches the latest releases from GitHub (stable and nightly), compares with the current pinned version, lets the user pick a target version, and updates all version references across the repo. Use when the user wants to bump or upgrade flashinfer.NVIDIA/TensorRT-LLM14,022
- Trtllm Model Onboard MultimodalOnboard a HuggingFace multimodal model (vision/audio/video + text) to the TensorRT-LLM PyTorch backend. Use when writing a new `tensorrt_llm/_torch/models/modeling_<vlm>.py` plus its input processor and weight mapper, or extending an existing VLM. Not for AutoDeploy — use `ad-model-onboard` for that path.NVIDIA/TensorRT-LLM14,022
- Trtllm Moe DevelopReview, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whetNVIDIA/TensorRT-LLM14,022
- Trtllm Serve Config GuideGenerate a source-backed starting `trtllm-serve --config` YAML for basic aggregate single-node PyTorch serving, aligned with checked-in TensorRT-LLM configs and deployment docs. Preserves explicit latency / balanced / throughput objectives. Excludes disaggregated, multi-node, and non-MTP speculative configs.NVIDIA/TensorRT-LLM14,022