「perf」の検索結果

Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.

日本語の概要は準備中です。原文の説明を表示しています。

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.

日本語の概要は準備中です。原文の説明を表示しています。

Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online packing, and CP constraints.

日本語の概要は準備中です。原文の説明を表示しています。

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

日本語の概要は準備中です。原文の説明を表示しています。

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

日本語の概要は準備中です。原文の説明を表示しています。

Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.

日本語の概要は準備中です。原文の説明を表示しています。

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

日本語の概要は準備中です。原文の説明を表示しています。

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

日本語の概要は準備中です。原文の説明を表示しています。

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.

日本語の概要は準備中です。原文の説明を表示しています。

Run `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or BlueField Arm. Use it to discover enabled benchmark libraries, capture a reproducible command/version/device/environment baseline, compare stable runs against a declared tolerance, or diagnose configuration, device-binding, workload-precondition, and measurement failures. Trigger for requests such as measuring BlueField compression speed, NIC RDMA throughput, crypto latency, or a pre-upgrade baseline. Do not use for application end-to-end timing, custom benchmark code, DOCA installation, or binary patches.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call returning DOCA_ERROR_*, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime → program → driver), verbosity controls (--sdk-log-level, DOCA_LOG_LEVEL, the doca-{lib}-trace flavor), container-debug constraints, or how to capture state for a Developer Forum post. Trigger even when the user does not say "DOCA debug" — implicit phrasings include "undefined reference to doca_*", "how do I get more logs", "packets aren't reaching the wire", "doca_caps returned nothing", or "hugepages empty in the container". Refuse and route elsewhere for library-specific debug (Flow pipe trace, RDMA QP, Comch stats), env-class pkg-config or hugepages symptoms, the DOCA_ERROR_* taxonomy and lifecycle interpretation, and performance or incident-response work — those belong to other skills.

日本語の概要は準備中です。原文の説明を表示しています。

NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline using NVIDIA BioNeMo NIMs: generate drug-like molecules with GenMol, dock them to a protein target with DiffDock, then predict binding affinity with Boltz2. Use this skill whenever the user wants to generate and screen small molecule drug candidates, perform hit discovery, optimize leads against a protein target, or do virtual screening combining molecule generation, docking, and affinity prediction. Triggers on: drug discovery pipeline, hit discovery, lead optimization, virtual screening, molecule generation, molecular docking, binding affinity, GenMol, DiffDock, Boltz2, SMILES, SAFE notation, NIM microservice. This is a multi-step pipeline composing three BioNeMo NIMs.

日本語の概要は準備中です。原文の説明を表示しています。

Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.

日本語の概要は準備中です。原文の説明を表示しています。

Perform multi-round web research on a topic, synthesize the findings, and file structured results into the Obsidian wiki. Use for comprehensive web-sourced research intended to become wiki knowledge.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill when OpenStoryline is already installed and the user wants to start the local MCP/Web services, create or continue a session, send editing instructions, perform multi-turn re-editing, and verify rendered video outputs, as well as Chinese requests like “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “用 OpenStoryline 剪视频”.

日本語の概要は準備中です。原文の説明を表示しています。

Golang data structures — slices (internals, capacity growth, preallocation, slices package), maps (internals, hash buckets, maps package), arrays, container/list/heap/ring, strings.Builder vs bytes.Buffer, generic collections, pointers (unsafe.Pointer, weak.Pointer), and copy semantics. Use when choosing or optimizing Go data structures, implementing generic containers, using container/ packages, unsafe or weak pointers, or questioning slice/map internals. Not for applying optimization patterns once profiling has identified a bottleneck (→ See `samber/cc-skills-golang@golang-performance` skill).

日本語の概要は準備中です。原文の説明を表示しています。

GitHub Actions CI/CD pipeline configuration for Golang projects — workflow files for test, lint, SAST, coverage and vulnerability-scan jobs, Dependabot and Renovate config files, GoReleaser release pipelines, Docker build/push, repository security settings, and AI-driven PR review. Use when setting up or improving Go project CI, writing or fixing `.github/workflows/*.yml`, adding a linter or security scanner as a pipeline job, wiring automated dependency-update bots, or adding quality gates. Covers wiring tools into a pipeline, not the analysis they perform: do NOT use for choosing or interpreting security findings (→ See `samber/cc-skills-golang@golang-security` skill) or for choosing, upgrading, or auditing dependency versions (→ See `samber/cc-skills-golang@golang-dependency-management` skill).

日本語の概要は準備中です。原文の説明を表示しています。

Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, races, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve, race detection, GODEBUG tracing, and production debugging. Start here for any 'something is wrong' situation. Not for interpreting profiles or benchmarking (→ See `samber/cc-skills-golang@golang-benchmark` skill), applying optimization patterns (→ See `samber/cc-skills-golang@golang-performance` skill), or designing new code (→ See `samber/cc-skills-golang@golang-safety` skill for defensive coding, `samber/cc-skills-golang@golang-concurrency` skill for concurrency design).

日本語の概要は準備中です。原文の説明を表示しています。

Golang skills orchestrator — always active on any Golang coding, review, debug, or setup task. Reads the task context and loads the most relevant skills from samber/cc-skills-golang, often multiple at once: writing a gRPC service loads golang-grpc + golang-testing + golang-error-handling; debugging a panic loads golang-troubleshooting + golang-safety; auditing security loads golang-security + golang-lint + golang-safety. Also: disambiguates competing clusters when two skills seem to overlap (performance vs benchmark vs troubleshooting, samber/lo vs mo vs ro, DI cluster, safety vs security), and configures the project's agent-config file (CLAUDE.md, AGENTS.md, GEMINI.md, Cursor rules, or Copilot instructions) to force-trigger skills in a project (/golang-how-to configure).

日本語の概要は準備中です。原文の説明を表示しています。

Audit openai-go during scheduled or repeated maintainer runs for correctness bugs, security weaknesses, performance problems, rough edges, non-idiomatic Go, test gaps, code organization, and architecture, then report one prioritized recommendation with evidence. Use for recurring proactive repository maintenance and rotating whole-codebase review; do not use for feature work, code changes, autonomous publishing, or pull-request stewardship.

日本語の概要は準備中です。原文の説明を表示しています。

Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.

日本語の概要は準備中です。原文の説明を表示しています。

Solves CTF challenges by performing first-pass triage, identifying the dominant category, and routing execution to the right specialized ctf-* skill. Use when the user gives you a challenge bundle, a remote service, a suspicious file, or only a vague challenge description and you must determine where to start. Do not use it when the category is already clear and a specialized skill can be invoked directly; this is the dispatcher and recon entrypoint, not the deepest reference for category-specific techniques.

日本語の概要は準備中です。原文の説明を表示しています。