「latency」の検索結果

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

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。

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

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。

Capture and interpret iOS Simulator ETTrace profiles. Use when profiling launch or runtime latency, comparing traces, or finding CPU-heavy stacks.

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。

When the user wants to define GTM metrics, build a metrics dashboard, measure pipeline efficiency, or track AI product performance. Also use when the user mentions 'GTM metrics,' 'revenue latency,' 'pipeline metrics,' 'TTFV,' 'time-to-first-value,' 'data health,' 'attribution,' 'conversion rate,' 'CAC,' 'LTV,' 'NRR,' 'GTM dashboard,' 'magic number,' 'pipeline velocity,' or 'funnel metrics.' This skill covers GTM measurement from metric selection through dashboard design, including AI-specific cost metrics, attribution models, and weekly review cadences. Do NOT use for technical implementation, code review, or software architecture.

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。

Diagnose demonstrated CPU, command latency, allocation or IO regressions in an owned process with controlled measurements and language-appropriate profilers. Route benchmark effectiveness, score growth and trajectory efficiency to loopx-benchmark; profiling does not qualify a budget or grant execution authority.

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。

The way to answer "how are my production AI agents doing?" and to run the team's agent-observability deployment — reach for it even on casual phrasing that names no tool. Trigger when the user wants to: • inspect agent telemetry — did agents error/fail/go flaky; sessions, events, latency, token usage, slowest models; eval/quality scores and whether quality dropped; • operate the deployment — ack/assign/resolve/mute/dismiss issues (alerts, reports, and audit findings) with notes; run and triage audits; see who has access and change roles (e.g. read-only); create or scope API keys (e.g. a push-only CI key); change settings; run saved or ad-hoc ClickHouse queries. Served by the `fp` CLI against FailproofAI Cloud. NOT for writing or designing an evaluator service / scoring logic (that's `agenteye-evaluator`), adding SDK/instrumentation to your app (that's `failproofai-sdk`, imported as `failproofai_sdk`), debugging the collector/daemon, or unrelated dev work (why a build/CI run failed, rotating non-FailproofAI Cloud secrets).

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。

Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and render fanout, implement semantically safe fixes, and verify behavior plus repository budgets. Use for trace files, reported profiling durations or call chains, dropped frames, long tasks, resize or scroll jank, render storms, layout thrashing, selector hot paths, interaction latency, or requests to locate exact source-level bottlenecks.

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 local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

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。

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.

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 invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load, parameterize, start, observe, or stop a Programmable Congestion Control (SPCX) algorithm on a BlueField with a DPA processor against a live RDMA / RoCE fabric, or picking SPCX vs the established `doca-pcc` surface. Trigger even when the user does not say "DOCA SPCX" or "doca_spcx_cc" — typical implicit phrasings include "I want to write a custom RTT-based CC algorithm for my RoCE fabric", "my SPCX session loaded but throughput / latency didn't change", "doca_pcc status shows Active but factory CC seems to still be in charge", "DOCA_PCC_PS_ERROR on start", "is the programmable-CC surface available on my install", or "DPA-side algorithm image won't load". Refuse and route elsewhere for DPA-side algorithm authoring detail, factory PCC firmware configuration, read-only PCC counter inspection, raw DPA cycle profiling, RDMA library programming, or general DOCA install — 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。

Use this skill when the user is measuring the host or DPU-CPU control-plane rate of a DOCA Flow pipeline with doca_flow_perf — picking a JSON policy from configs/, choosing the DPDK or DOCA backend, running the single-iteration smoke then the iterative eval loop, interpreting per-iteration CPU cycles and num_pushed / num_failed, or capturing the four-tuple (DOCA version, BlueField/firmware, JSON policy, worker/queue/burst config) that makes a Kops/sec number defensible. Trigger even when the user does not explicitly mention "doca-flow-perf" — typical implicit phrasings include "how many rules per second can my BlueField insert", "5-tuple hairpin rule rate", "Kops/sec for steering", "flow-perf number does not match release notes", "DPDK vs DOCA benchmark", or "rule-install variance too high". Refuse and route elsewhere for optimizing a live Flow app (doca-flow-tune), the DPA-offloaded path (doca-flow-dpa-perf), dataplane throughput or latency, or library-internal pipe semantics — 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。

Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the client posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandwidth on a GPU+IB-device pair. Trigger even when the user does not explicitly mention "doca-gpunetio-ib-write-bw" or "GPUNetIO" — typical implicit phrasings include "measure WRITE BW when the GPU posts the WRs", "BW swings between runs on the same flags", "is the NIC saturated or am I CPU-bound on the CUDA kernel", "meson compile fails for the GPUNetIO bw tool", "nvidia_peermem isn't picking up my GPU buffer", or "GPU-initiated WRITE throughput vs CPU-initiated perftest". Refuse and route elsewhere for general doca-gpunetio library work, DOCA install, the GPU-initiated WRITE latency analog, the CPU-initiated upstream perftest, or application-level end-to-end throughput — 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。

Use this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta), running offline or online (read-only or state-changing) modes, reading the dumper CSV / analyze JSON / visualize mermaid, or applying a recommendation back into the Flow program. Trigger even when the user does not explicitly mention "doca_flow_tune" — typical implicit phrasings include "Flow rule-install rate is low on BlueField", "table sizing looks wrong for this pipe", "tune visualize step is empty", "before/after counters don't move", or "which doca-flow knob does this recommendation hit". Refuse and route elsewhere for measuring baseline numbers (doca-flow-perf, doca-flow-dpa-perf), writing the doca-flow application, DOCA install, or streaming Flow telemetry — 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。

In-memory caching in Golang using samber/hot — eviction algorithms (LRU, LFU, TinyLFU, W-TinyLFU, S3FIFO, ARC, TwoQueue, SIEVE, FIFO), TTL, cache loaders, sharding, stale-while-revalidate, missing key caching, and Prometheus metrics. Apply when using or adopting samber/hot, when the codebase imports github.com/samber/hot, or when the project repeatedly loads the same medium-to-low cardinality resources at high frequency and needs to reduce latency or backend pressure.

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。

Create text-driven visuals in Markdown: charts, diagrams, cards, architecture and page layouts. Charts and analytical views (bar, line, pie, heatmap, correlation, regression); reliability and operations (latency, incident, throughput, cycle time, OKR, standup, on-call); product and finance (funnel, retention, revenue, budget); process and workflow (approval, BPMN); software design and behaviour (class, state machine, sequence, C4); dependencies and impact (dependency graph, ER, causality); system architecture as HTML (layer stack, wings, zones, topology, service catalogue, request paths); infrastructure (cloud, Kubernetes, ETL, network, security, IAM, compliance); governance and people (ArchiMate, org chart, hiring); knowledge and planning (mind map, roadmap, Gantt, migration); documents (comparison, SWOT, memo, policy, catalogue, case study). Use when a document needs a diagram, chart or card. Figures render live. Not for slide decks or math notation. Not recommended: mermaid / canvas / drawio / dot.

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。

The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are prompt bytes, and verification. Load when writing or reviewing a commerce agent's prompt assembly, when cache reads are zero, or when a turn's latency or cost is the question.

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。

Design waiting experiences — spinners, skeletons, optimistic updates, and progressive reveal. Use when content takes time to arrive. For the latency budget itself use `doherty-threshold`; for success confirmation use `feedback-patterns`.

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 when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.

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。

Operate a live AWS workload with AWS DevOps Agent — incident investigation, root-cause analysis, and release-readiness review — for startups with no dedicated DevOps or SRE engineer. Use when a live AWS workload is misbehaving (production is down, 5xx errors, latency spike, timeouts, it broke after the last deploy, an alarm fired, a pasted CloudWatch alarm or stack trace, find the root cause, write a postmortem, no one on call), for pre-merge review (is this PR safe to ship, blast radius), or to set up, pause, stop, or check the cost of AWS DevOps Agent. Detects existing setup first and never re-onboards. Cost, account access, and code egress are each disclosed in one line with safe defaults: cost and access proceed, code egress stays off unless asked. Do not use for: new architecture (architect-for-startups), scaffolding (start-building-for-startups), migrations (gcp-to-aws, azure-to-aws, heroku-to-aws, llm-to-bedrock), or general Activate and credits questions (knowledge-base-for-startups).

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 a deep root-cause investigation on the AWS DevOps Agent. Use when the user describes an incident, alarm, outage, or unexplained behavior — keywords like "5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "investigate", "root cause", "debug", "alarm fired", "service down". Polls and streams progress, then surfaces recommendations.

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。

Plans, builds, runs, and analyzes fault injection experiments with AWS Fault Injection Service (AWS FIS) to validate application resilience through chaos engineering. Covers experiment templates (actions, targets, stop conditions), the FIS actions catalog and action selection, the scenario library (AZ power interruption, cross-Region connectivity, EC2/EKS/EBS stress), experiment lifecycle and monitoring, logging and reports, multi-account experiments, the experiment IAM role, and blast-radius safety. Applies when a user mentions AWS FIS or fault injection, asks what experiment to run for a failure mode (AZ, Region, API errors/throttling, instance/pod/DB/cache failure, latency, packet loss), wants to author an experiment template or CLI/CloudFormation, or needs to safely run chaos experiments in pre-production or production. For the broader resilience program across Resilience Hub and ARC, see aws-resilience-lifecycle; for ARC routing controls and zonal shift, see recovery-controller-setup.

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。

Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.

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。

Analyze and improve Attio integration latency and throughput from measured query shape, pagination, concurrency, retry, and cache evidence while preserving correctness. Use when Attio requests are slow or queues are backing up. Trigger with "Attio performance", "speed up Attio sync", or "Attio query tuning".

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。

Set up observability for Claude API integrations with metrics, logging, and alerting for latency, cost, errors, and token usage. Trigger with phrases like "anthropic monitoring", "claude observability", "anthropic metrics", "track claude usage", "claude dashboard".

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。