342 个 · 按相关度排序
Integrate Flash Attention into transformer models to reduce processing time and GPU memory use for long sequences. Covers PyTorch integration, advanced attention options, and benchmarks that compare speed, memory use, and output accuracy.
中文简介正在准备中。当前显示英语简介。
Optimize transformer attention, the calculation that relates tokens to one another, using Flash Attention. The skill guides PyTorch integration, GPU memory reduction, performance measurement, and output comparisons for training or inference with long sequences.
中文简介正在准备中。当前显示英语简介。
attention notification watcher（承認待ち / 判断待ち / CI 失敗等を OS 通知 + 音で能動通知）を dispatcher ペインの右側に split で常駐起動する。`.state/attention.json` が未配置なら ja 既定テンプレートを `tools/templates/attention.example.json` から自動コピーする。 起動後のペイン id は `.state/attention_pane.json` に記録し、`/org-attention-stop` から参照する。 「attention 起動」「通知監視を始めて」「watcher を立てて」等で発動。 `/org-start` からの auto-start はしない（明示起動推奨ポリシー）。
中文简介正在准备中。当前显示原文说明。
`/org-attention-start` で起動した attention watcher ペインを停止する。 `.state/attention_pane.json` に記録された pane_id を `list_panes` の name/role で identity 確認し、いまも attention watcher を指している場合だけ `close_pane`（pane 破棄）で 破棄する（pane_id が別ペインへ再割当て済みなら close せず stale sidecar として削除）。 「attention 止めて」「通知監視を停止」「watcher 落として」等で発動。
中文简介正在准备中。当前显示原文说明。
为处理长输入的Transformer模型接入Flash Attention，加快训练与推理中的注意力计算并减少GPU显存占用，涵盖安装、性能测量和输出比较。
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
中文简介正在准备中。当前显示原文说明。
The runbook a triage agent follows on each run over the super-admin attention dock, through the attention MCP tool. Use when a scheduled attention-triage routine wakes, when asked to triage, clean up or shrink the attention dock or admin alerts, or when the dock's card is over budget.
中文简介正在准备中。当前显示原文说明。
Learn how instructions, documents, tool results, and conversation history form an AI model’s context. Understand attention limits, why information in the middle can be missed, and how relevance and placement inform decisions about what to include.
中文简介正在准备中。当前显示英语简介。
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.
中文简介正在准备中。当前显示原文说明。
Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by WanVideoWrapper / many video graphs). Windows-first (triton-windows + woct0rdho prebuilt SageAttention wheels matched to torch/CUDA/python into the RIGHT python), plus Linux (official triton + build) and Mac (N/A → sdpa/MPS). Also covers the SAFE sdpa / no-compile fallback so an example that assumes sageattn + torch.compile still runs when these aren't installed (video-extend TRAP 5). Use when a loader crashes with "No module named 'sageattention'" or reports triton unavailable, when asked to speed up Wan/video workflows, or when deciding whether to install acceleration vs. fall back.
中文简介正在准备中。当前显示原文说明。
Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.
中文简介正在准备中。当前显示原文说明。
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
中文简介正在准备中。当前显示原文说明。
测量claude-flow v3的启动时间、搜索速度和内存用量，验证是否达到改进目标，并通过持续监测发现性能退化，为优化方案提供依据。
Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.
中文简介正在准备中。当前显示英语简介。
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
中文简介正在准备中。当前显示英语简介。
Explore how coordinating agents can pass relevant working state to workers through KV cache, a model's internal attention memory. Covers task-specific selection, runtime requirements, and comparisons of accuracy, token use, and processing overhead.
中文简介正在准备中。当前显示英语简介。
Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.
中文简介正在准备中。当前显示英语简介。
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
中文简介正在准备中。当前显示英语简介。
Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.
中文简介正在准备中。当前显示英语简介。
Shape output for a reader with ADHD, then write each sentence in controlled English: action first, one word one meaning, active voice, simple tenses, state restated every turn. Invoke with /attention-control; stays on until "stop attention control".
中文简介正在准备中。当前显示原文说明。
从目标读者的角度试读发布前的文稿，检查是否愿意打开、在哪里失去兴趣，以及读后记住什么。它报告模拟读者的反应，不改写文章。
Calculate how to divide serving memory between recurrent state and KV cache, two memory pools used by hybrid models. Use startup logs and workload settings to recommend a ratio, estimate concurrency, and identify the limiting pool.
中文简介正在准备中。当前显示英语简介。
Set up LLM serving with structured responses, including JSON and outputs restricted to specified patterns. Covers reusing shared prompt calculations, tool calling, and multi-turn conversations through SGLang, with examples for server setup and application integration.
中文简介正在准备中。当前显示英语简介。
Build LLM serving workflows that produce JSON or other required formats. The skill covers reusing computation for shared prompts, tool calls, and ongoing conversations, with examples for server setup and structured output.
中文简介正在准备中。当前显示英语简介。