221 个 · 按相关度排序
Use when evaluating a newly adapted model's accuracy/eval score. Runs evalscope eval (or the test/srt/run_eval.py fallback) against an OpenAI-compatible endpoint on datasets like gsm8k / aime, producing per-dataset reports and a score. Accuracy only — throughput/latency benchmarks belong to model-speed-benchmark. Triggers on accuracy, eval, evalscope, gsm8k, aime, run_eval — not throughput.
中文简介正在准备中。当前显示原文说明。
Load tests API endpoints with progressive concurrency. Measures response times, error rates, throughput, and identifies breaking points. Generates a detailed report with latency percentiles, throughput curves, bottleneck analysis, and optimization recommendations.
中文简介正在准备中。当前显示原文说明。
Plan, diagnose, and verify performance budgets, latency targets, load tests, capacity estimates, bottleneck analysis, caching strategy, query efficiency, queue throughput, and regression gates. Use when a feature may be slow, a system must scale, a performance regression is suspected, or release readiness depends on throughput, cost, memory, CPU, or response time.
中文简介正在准备中。当前显示原文说明。
Performance optimization mindset - knowing when to optimize, how to measure, where bottlenecks hide, and when "fast enough" is the right answerUse when "slow, performance, optimize, profiling, benchmark, latency, throughput, cache, n+1, bottleneck, memory leak, too slow, speed up, response time, performance, optimization, profiling, caching, latency, throughput, big-o, benchmarking" mentioned.
中文简介正在准备中。当前显示原文说明。
Analyze Kanban flow metrics to identify bottlenecks and improve team throughput. Covers Cycle Time, Throughput, WIP, and Flow Efficiency using Little's Law and Theory of Constraints. Use when a team wants to optimize delivery flow or improve predictability. Do not use for sprint-based Scrum planning — use sprint-planning-assistant instead.
中文简介正在准备中。当前显示原文说明。
Analyze flow metrics to identify delivery bottlenecks and improve throughput. Use when the user says "flow metrics", "why is delivery slow", "cycle time analysis", "WIP analysis", "throughput review", "what's our lead time", "DORA metrics", "where is work getting stuck", "Kanban metrics", or wants to diagnose delivery performance using data - even if they don't explicitly say "flow metrics review". Based on "Making Work Visible" by Dominica DeGrandis (WIP limits, flow blockers, time thieves) and "Accelerate" by Forsgren, Humble & Kim (DORA metrics, delivery performance indicators).
中文简介正在准备中。当前显示原文说明。
Expert-level materials informatics covering materials databases, machine learning for property prediction, high-throughput computation, and data-driven materials discovery.
中文简介正在准备中。当前显示原文说明。
Systematically find and fix performance problems in applications, frontend and backend, by measuring first. Use this skill whenever the user reports slow endpoints, high latency, poor throughput, memory leaks, large bundles, or slow page loads; wants to profile with cProfile, py-spy, Chrome DevTools, Node --cpu-prof, or perf; run load tests with locust or k6; set performance budgets or SLOs; optimize database queries (EXPLAIN, indexes, N+1); add caching (Redis); improve frontend performance (code splitting, lazy loading, image optimization, memoization, virtualization); or tune the network (CDNs, gzip/br, HTTP/2/3). Also trigger for p50/p95/p99 latency, throughput, error rate, connection pooling, async vs threads, GIL, and memory leak investigations.
中文简介正在准备中。当前显示原文说明。
Comprehensive, measurement-driven performance optimization for latency, throughput, memory/GC, and tail behavior. Use when the user asks to optimize/speed up, reduce latency (p95/p99), increase throughput/QPS, lower CPU/memory/allocations/GC pauses, profile hot paths, or run a benchmarked perf pass (including JSONL/query-heavy code). Requires before/after measurement on a runnable workload (or an explicit `UNMEASURED` plan) plus a correctness gate.
中文简介正在准备中。当前显示原文说明。
Check task processing statistics to see how much data and how many docs are moving. Use when checking throughput, diagnosing a stalled task, verifying data movement, or reporting on task activity. Use when user says "is data flowing", "how much data", "check throughput", "how many documents", "task not processing", "data not arriving", "stats", "bytes processed", "stalled capture", "no data in destination", "data volume", "task report", "usage report", or "how much data did we process".
中文简介正在准备中。当前显示原文说明。
NVIDIA RAG Blueprint performance-tuning guidance for profiling retrieval stacks, comparing bottlenecks, and validating latency or throughput improvements.
中文简介正在准备中。当前显示原文说明。
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Apply systematic performance optimization techniques when writing or reviewing code. Use when optimizing hot paths, reducing latency, improving throughput, fixing performance regressions, or when the user mentions performance, optimization, speed, latency, throughput, profiling, or benchmarking.
中文简介正在准备中。当前显示原文说明。
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
中文简介正在准备中。当前显示原文说明。
分别衡量实时界面与数据推送的延迟、数据新鲜度和待处理任务，梳理事件发生到屏幕显示的完整路径，逐段改进，并在运行环境中验证结果。
分阶段排查大量数据导入、历史补录、转换和同步的耗时，比较处理方法并加速，在执行后核对文件数、行数与时间戳的一致性，形成可重复使用的流程。
帮助在NVIDIA GPU上加速大语言模型的响应生成，并通过API提供服务。支持量化、批量处理和多GPU分布运行，以调整显存占用与服务性能。
Measure throughput, response times, and resource use for systems and groups of agents. Use baseline comparisons, load tests, and performance criteria to identify slowdowns, assess behavior under pressure, and summarize results with recommendations.
中文简介正在准备中。当前显示英语简介。
Improve workflows involving multiple AI agents by measuring bottlenecks, adjusting workload distribution, and managing model costs. This design guide helps compare changes against a measured baseline while checking quality, latency, and resource use.
中文简介正在准备中。当前显示英语简介。
Design KPI dashboards that help teams make decisions using clearly defined performance measures. Choose relevant metrics, organize summary and detail views, document calculations, and address inconsistent figures, database load, and excessive alerts.
中文简介正在准备中。当前显示英语简介。
Investigate SGLang serving failures by collecting server state, preserving failing requests, and replaying them on a clean target. Summarize evidence and likely causes, then choose the next debugging tool for crashes, stalls, or performance regressions.
中文简介正在准备中。当前显示英语简介。
Deploy Suricata to detect suspicious network traffic or block it inline. Configure protocol inspection, detection rules, and structured EVE JSON logs, then connect logs to analysis platforms and check packet drops and alert quality during operation.
中文简介正在准备中。当前显示英语简介。
Guides large language model reinforcement learning with miles, covering environment setup, low-precision training, consistency between training and inference, and speculative decoding, where a smaller model proposes tokens for a larger model to verify.
中文简介正在准备中。当前显示英语简介。