「throughput」の検索結果

Interactively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling.

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。

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。

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。

Analyze and optimize system throughput including request handling, data processing, and resource utilization. Use when identifying capacity limits or evaluating scaling strategies. Trigger with phrases like "analyze throughput", "optimize capacity", or "identify 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。

Use when running throughput/latency (serving speed) benchmarks against an already-running model server. Uses sgl_jax.bench_serving to sweep batch-size/concurrency and measure throughput and latency, producing summary.csv and per-point bs_<N>/result.jsonl. Speed only — accuracy/eval belongs to model-accuracy-benchmark. Triggers on throughput, latency, bench_serving, batch-size sweep, tok/s, TTFT, TPOT — not accuracy/eval.

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。

Serve LLMs com alta throughput usando PagedAttention do vLLM e continuous batching. Use ao fazer deploy de APIs LLM em produção, otimizar latência/throughput de inferência, ou servir modelos com memória GPU limitada. Suporta endpoints compatíveis com OpenAI, quantização (GPTQ/AWQ/FP8) e 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。

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。

処理の高速化を、現状の計測、仮説ごとの変更案の比較、正しさの検証へ分解し、時間や費用の上限内で最も速い安全な案と再実行できる手順を残すスキル。

• 遅い処理を計測しながら高速化したいとき
• 同じ入力条件で実装案を比較したいとき
• 応答時間・処理量・実行費用の評価

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.

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 GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (`gcloud alpha mldiagnostics monitored-events` / `hypercomputecluster.googleapis.com/v1alpha`) and 1-minute Cloud Monitoring system metrics (`kubernetes.io/node/accelerator/*`). Distinguishes hardware and network fabric throttling from workload resource bottlenecks (HBM capacity, host memory, or host CPU saturation). Use when TPU training throughput or duty cycle drops without crashing pods, when `PERFORMANCE_DEGRADATION` monitored events fire, or when triaging slow multi-slice training steps. Don't use for complete multi-slice XLA execution stalls with `HANG_DETECTED` logs (use gke-ai-troubleshooting-tpu-mxla-hang) or pod eviction/interruption restarts (use gke-ai-troubleshooting-jobset-interruption).

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。

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/stas00/ml-engineering/blob/master/skills/ml-engineering/SKILL.md

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。

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.

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 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。

[omh] AI agent progress for managers: help managers inspect AI-agent progress, blockers, quality gates, and throughput levers. Use when the user says: agent-ops-review, agent ops review, agent productivity, operator productivity, manager view, quality dashboard, throughput review, agent work quality.

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 account-aware Alchemy throttling, bounded retries, and admission control from observed throughput rather than stale plan constants. Use when preventing or handling rate limits. Trigger with "Alchemy rate limit", "Alchemy throughput", or "fix Alchemy 429s".

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 performance issues on Amazon SageMaker HyperPod clusters — uneven NCCL bandwidth across nodes and poor filesystem throughput. Read-only. Surfaces host-side signals (Xid, ECC, NVLink, EFA reachability, FSx saturation) and routes to the appropriate sibling skill (hyperpod-node-debugger, hyperpod-nccl, hyperpod-version-checker, hyperpod-issue-report) for any remediation. Triggers on uneven NCCL across nodes, straggler node, FSx slow, checkpoint slow, dataloader slow, filesystem bottleneck, FSx throughput, cross-AZ latency, topology mismatch.

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 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.

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。

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.

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。

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.

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。

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.

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 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.

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 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).

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。

Expert-level materials informatics covering materials databases, machine learning for property prediction, high-throughput computation, and data-driven materials discovery.

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。