「offload」の検索結果

Use this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type, sizing buffers via the doca_dma_cap_task_memcpy_* queries, setting LOCAL_READ_ONLY / LOCAL_READ_WRITE permissions on source / destination doca_mmap regions (plus doca_mmap_export_* for cross-peer copies), driving the progress engine, or debugging DOCA_ERROR_* returns. Trigger even when the user does not explicitly mention "DOCA DMA" or "doca_mmap" — typical implicit phrasings include "memcpy host buffer to BlueField without using the CPU", "offload a bulk copy to the DPU", "copy returns NOT_PERMITTED on first submit", "buffer too big for one DMA task", "task submitted but no completion", or "scatter-gather copy between two memory regions". Refuse and route elsewhere for cross-network copies (DOCA RDMA), producer/consumer messaging (DOCA Comch), DOCA Core / progress-engine internals, or 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 for hands-on DOCA Ethernet packet-queue work on a BlueField DPU or ConnectX NIC — bringing up a `doca_eth_rxq` or `doca_eth_txq` on a port / representor / SF, picking among the four `enum doca_eth_rxq_type` values (`_REGULAR` / `_CYCLIC` / `_MANAGED_MEMPOOL` / `_SHARED_MEMPOOL`), sizing burst or scatter-gather length against the `_cap_*` queries, submitting `doca_eth_txq_task_send` / `_lso_send` (carrying packet `doca_buf`s — no `doca_eth_frame` struct exists), or debugging DOCA_ERROR_* from an Ethernet call. Trigger on implicit phrasings: "my RX queue is up but no packets arrive", "send-task returns AGAIN at line rate", "which queue type for fixed-MTU ingress", "device open fails without sudo", or "is L3 checksum offload available here". Refuse and route elsewhere for installing DOCA, flow-rule / steering programming, host↔DPU control messaging, or RDMA data movement.

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。

Use this skill when the user is invoking doca_flow_dpa_perf on DPA-capable hardware (ConnectX-7 minimum supported, ConnectX-8 recommended, or BlueField-3) to measure rule update / disable rates on the DPA-offloaded DOCA Flow path — picking the active / passive device split, choosing workload-shape axes (burst, queue, completion threshold, workers, hash pipe algo, PSL tables), or reading Kops/sec iteration stats and the optional self-test. Trigger even when the user does not explicitly mention "doca_flow_dpa_perf" or "DPA Provider" — typical implicit phrasings include "how fast can the DPA program path-selector entries", "baseline rule-update rate on ConnectX-8", "tool reports zero ops on my BlueField", "self-test sentinel never shows on tcpdump", or "is my BlueField-2 DPA-capable". Refuse and route elsewhere for the host / DPU-CPU Flow path (doca-flow-perf), Flow pipeline tuning (doca-flow-tune), writing doca-flow / doca-dpa applications, or 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。

Resolve Swift concurrency compiler errors, adopt approachable concurrency (SE-0466), and write data-race-safe async code. Use when fixing Sendable conformance errors, actor isolation warnings, or strict concurrency diagnostics; when adopting default MainActor isolation, @concurrent, nonisolated(nonsending), or Task.immediate; when designing actor-based architectures, structured concurrency with TaskGroup, or background work offloading; or when migrating from @preconcurrency to full Swift 6 strict concurrency.

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。

Redesign a direct instruction sequence to include productive struggle before the explanation phase. Use when teaching concepts that benefit from failure-first approaches.

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。

Implement distributed cron jobs with Redis-based locking and BullMQ offloading in NestJS. Use when adding @Cron scheduled tasks, preventing duplicate runs across pods, or delegating heavy work to queue workers.

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 Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

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。

Autonomous sub-agent hand-off for a fiddly, fully-specified exploit-compile / escalation RUN - the main agent stays on strategy and the board while a cheap sub-agent runs an exact copy-paste checklist behind a false-root/hostname guardrail. Use for "delegate", "offload", "hand this to a sub-agent", "spin a haiku", or the moment a foothold plus a working escalation vector is identified. Main agent dispatches, waits (no parallel duplicate), integrates the result.

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。

Kaggle-first end-to-end competition workflow for scored submissions. Use when Codex must run Kaggle or competitive ML workflows through scored submission, including code competitions, validation, metrics, policy-safe public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling/stacking, proactive multi-notebook architectures, producer notebooks that train models and export private Kaggle artifact datasets, downstream consumer notebooks, Kaggle GPU offload, kagglehub access, hidden-test debugging, and public score retrieval.

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。

Kaggle-first end-to-end competition workflow for scored submissions. Use when Codex must run Kaggle or competitive ML workflows through scored submission, including code competitions, validation, metrics, policy-safe public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling/stacking, proactive multi-notebook architectures, producer notebooks that train models and export private Kaggle artifact datasets, downstream consumer notebooks, Kaggle GPU offload, kagglehub access, hidden-test debugging, and public score retrieval.

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 background tasks in Python with Celery. Use when a user asks to process tasks asynchronously, schedule periodic jobs, run background workers, build task queues in Python, or offload heavy processing from web requests.

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 coding tasks via opencode using free cloud models. Use when asked to offload work to opencode.ai or run a free model. Don't use for local models (Ollama, LM Studio), Claude/OpenAI calls, or when Claude should do the work itself.

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。

Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work. Use this whenever the user asks to spin off, offload, or delegate a task to Antigravity, agy, Gemini, or an "external agent"; wants a second opinion or independent review from a different model; wants intensive repo work (audits, large refactors, research sweeps) run in the background while you keep working; or says things like "have Antigravity do it", "spin up a sub-agent for this", or "get more done in parallel". Also use it proactively when a task is a good fit for parallel delegation and the user has expressed a preference for using Antigravity workers.

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。

[BETA] Offload plan phase to Claude Code's ultraplan cloud — drafts remotely while terminal stays free, review in browser with inline comments, import back via /gsd:import. Claude Code only.

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。

Redesign a direct instruction sequence to include productive struggle before the explanation phase. Use when teaching concepts that benefit from failure-first approaches.

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。

Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types.

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 tool outputs exceed 2000 tokens, tasks span multiple conversation turns, sub-agents need to share state, context window is bloating, plans need to persist across summarization, terminal/log output needs selective querying, or when user mentions "offload context", "dynamic context discovery", "filesystem memory", "scratch pad", "reduce context bloat", or "just-in-time context loading".

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。

优化域入口（L2）：拿到**已明确的瓶颈点 / 瓶颈标签**后，按标签把任务**分发**到四个优化模块 （DiT 计算 `dit-perf-opt` / DiT 通信 `dit-parallel-opt` / VAE `vae-opt` / host `host-opt`），并给出域内**最小前置集**与**域级验收口径**（性能入库口径引 `perf-gate`、精度判据引 `accuracy-gate`）。 **本技能不再承载选档与实施内容**（Step 2–4 闭环、特性档位选择、组合试验已全部归 `dit-perf-opt`）。 入口信号（任一即可触发）：① 用户或编排层已给出**瓶颈点/瓶颈标签**（"瓶颈已经明确，按这个点优化"）； ② **框架侧特性没落地**（该开的开关/特性没开，需要先判走哪个模块）。 near-miss（看似相关但不属本技能）： - **瓶颈未明**（"这个模型怎么加速""怎么跑通""采个 profile"，还要先定位）→ 先走 `model-auto-optimization`（唯一有分析权的一方），本入口**不接受未定位的任务**。 - 问"要不要开量化、开哪一档""量化/稀疏/Cache 怎么选怎么开" → `dit-perf-opt`（选档与实施在模块层）。 - 多卡并行形态 / 通信掩盖 / TP·offload → `dit-parallel-opt`；VAE·TAE 解码段 → `vae-opt`；交付搬运 / 装载预热等固定开销 → `host-opt`。 - 需要改本仓代码（pattern / 算子 / 测试 / 文档）→ `dev-workflow`。 由 model-auto-optimization 的阶段路由与用户直接声明瓶颈两条路径触发。

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。

DiT 计算模块（L3）：把**已定位的 DiT 计算瓶颈**落成特性级选档与实施—— 量化档（W8A16 / W4A16 / W8A8 系列 / W4A4 / MXFP8 / FA 量化）、稀疏（rf_v2 / ada_bsa）、 缓存（DiTCache / AttentionCache / 时间步优化）、编译启用（MindieSDBackend / Pattern 融合 / ACLGraph） 的**开不开、开哪一档、怎么开、怎么复验**；依据是 `docs/zh/features/*`（特性真源）+ framework-integration/references/framework-support-matrix.md（支持状态）。 即使用户只说"这个模型怎么加速""量化/稀疏/Cache 怎么选怎么开""要不要开量化、开哪一档""这个档位开了有没有效果" 而未提 profiling，也应触发。 **入口条件**：瓶颈点已明确（用户带一句实测锚点，或编排层交付标签）时由域入口 `performance-optimization` 按标签分发到本技能；**瓶颈未明（"怎么加速 / 跑通 / 采 profile"）先走 `model-auto-optimization` 定位**，不在本技能内做占比分析。 near-miss：多卡并行形态 / 通信掩盖 / TP·offload 选型 → `dit-parallel-opt`；VAE 解码段与 host 固定开销 → 各自模块（VAE / host）；单算子实现级实测选型（mindie_bench）→ `benchmark-dev`； 需要新增 pattern / 算子才能落地本档 → `pattern-dev` / `operator-dev`；框架侧开关与使能验证 → `framework-integration`；量化器位级契约与精度对齐（编码公式 / 舍入 / scale 粒度）→ `quantization-dev`；精度验收判据 → `accuracy-gate`；数字入库口径 → `perf-gate`。

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。

Delegate a prompt to Claude via `claude -p`. Use when the user wants to offload a task to Claude from another agent (Codex, Cursor, another Claude session), get a second opinion, or run a parallel implementation. Default model is opus.

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。

Drive the current task to a verified result instead of stopping at a plausible report. Use when the user says /continue, keep going, not done yet, push further, or is unhappy with the result. Rebuilds requirements from the conversation, re-checks real state, fixes root causes, verifies from the consumer side, offloads side quests.

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。

Resolve Swift concurrency compiler errors, adopt approachable concurrency (SE-0466), and write data-race-safe async code. Use when fixing Sendable conformance errors, actor isolation warnings, or strict concurrency diagnostics; when adopting default MainActor isolation, @concurrent, nonisolated(nonsending), or Task.immediate; when designing actor-based architectures, structured concurrency with TaskGroup, or background work offloading; or when migrating from @preconcurrency to full Swift 6 strict concurrency.

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。