“kernel”的搜索结果

**精度验收标准**：凡是"改动不应改变结果"的场合（等价替换、算子/子模块融合、并行切分、 编译与图下发、拷贝消减），都按本标准判"合格 / 不合格"——等价分层（L1 逐位 / L2 数值门 / L3 有损门）+ 三级验收序（① 同配置重跑逐位 → ② 跨配置数值门 + 产物 md5 不变 → ③ 质量门）+ 判据不达标时的排障入口。当用户说"这个算子能不能换个写法/换个 kernel/等价实现/ 无损替换""替换后结果会不会变""怎么证明逐位一致""结果不对""花屏""尾部塌了" "CPU 跑对 NPU 跑不对"，或发现某个 hotspot 占了大头（例如某类算子在阶段里占 90% 以上）想动手时， 都应触发；即使用户只说"这样改有没有把结果改坏""能不能判它是无损的"也应触发。 覆盖：等价分层与判据、满足本标准的实现约定（per-shape 对拍写进实现，把索引/相位/顺序类重写 错误在首次调用抓住）、per-shape 条件性等价（同一改动在不同形状下结论可能不同）、 判据不达标 → `references/silent-failure-localization.md` 排障入口、否决案例的形态学 （换写法未换 kernel / 差异极小仍非逐位 / 等价但 OOM）、以及收益口径的归属（性能数字一律交 `perf-gate`）。 **近义分流**：选量化档 / 特性选档（要不要开量化、开哪一档）→ `dit-perf-opt`； 并行选型（USP / CP / TP 怎么切）→ `dit-parallel-opt`；本技能只判"结果是否被改变"， 不负责选档与选型。

中文简介正在准备中。当前显示原文说明。

Reference for MCP Jupyter tools (kernel management, cell execution, Papermill). Use when executing notebooks, managing kernels, or running code interactively via MCP.

中文简介正在准备中。当前显示原文说明。

Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.

中文简介正在准备中。当前显示原文说明。

Iterative Python via live Jupyter kernel (hamelnb).

中文简介正在准备中。当前显示原文说明。

Use when developing, reviewing, debugging, porting, or engineering Linux kernel device drivers, kernel modules, device tree bindings, bus clients, subsystem drivers, DMA/IRQ/memory paths, userspace interfaces, or hardware bring-up plans.

中文简介正在准备中。当前显示原文说明。

Distill an already-built or near-launch product into one incisive brand kernel — the "reveal" already hiding in its name, story, or the product itself — then build the name, voice, visual identity, and a developer-ready handoff kit around it. This is LATE-STAGE branding: use it when there is a real, thought-through product that is about to launch, or already live but not explained in a way people grasp in an instant. Use whenever the user wants to name or rename a product, find a tagline or slogan, create a brand identity / brand kit / style guide / design system, design a logo, wordmark, palette, or type system, mock up a homepage for a launch, or hand brand assets to a coding agent (Claude Code, Codex, Cursor). Trigger even when the user only says their product needs to "land" or "feel like" something, or that they can't explain it simply yet. Do NOT use for half-baked, pre-product ideas with nothing to excavate — this skill extracts a kernel that already exists; it does not invent one from a blank canvas.

中文简介正在准备中。当前显示原文说明。

Implement eBPF-based runtime security observability and enforcement in Kubernetes clusters using Cilium Tetragon for kernel-level threat Tespit and policy enforcement.

中文简介正在准备中。当前显示原文说明。

Iterative Python via live Jupyter kernel (hamelnb).

中文简介正在准备中。当前显示原文说明。

Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel modules, and injected code from Linux memory images. Use when performing incident response on compromised Linux systems.

中文简介正在准备中。当前显示原文说明。

Apple グラフィックス。Metal, Core Animation, Core Graphics, Core Image, SpriteKit, SceneKit。 MTLDevice, MTKView, MTLBuffer, MTLTexture, MTLResidencySet, MTLTensor, Metal 4 (MTL4CommandQueue, MTL4CommandBuffer, MTL4CommandAllocator, MTL4ArgumentTable, MTL4RenderCommandEncoder, MTL4Compiler), CALayer, CABasicAnimation, CADisplayLink, CAMetalDisplayLink, CAMetalDrawable, CGContext, CGPath, CGImage, CIFilter, CIContext, CIImage, CIRAWFilter, CIWarpKernel, CIBlendKernel, SKScene, SKSpriteNode, SKAction, SCNNode, SCNGeometry, SCNMaterial。

中文简介正在准备中。当前显示原文说明。

Iterative Python via live Jupyter kernel (hamelnb).

中文简介正在准备中。当前显示原文说明。

Integrates AI/LLM via Semantic Kernel. Plugins, prompt templates, memory stores, agents.

中文简介正在准备中。当前显示原文说明。

You are helping a penetration tester exploit kernel vulnerabilities, vulnerable drivers,

中文简介正在准备中。当前显示原文说明。

You are helping a penetration tester exploit Linux kernel vulnerabilities and escape

中文简介正在准备中。当前显示原文说明。

Low-level keylogger architecture design: kernel driver hooks (WH_KEYBOARD_LL, SetWindowsHookEx), ETW-based input capture, user-mode vs kernel-mode approaches, stealth techniques, and data exfiltration. Use for understanding input capture mechanisms, EDR evasion research, or malware architecture analysis.

中文简介正在准备中。当前显示原文说明。

在Claude Code中设计多名专业代理协作的工作流程，将进度、决策和日志保存到文件，以便跨会话继续工作，并把重复任务整理为可复用命令和定期执行计划。

• 协调开发、写作和调研分工
• 跨会话保留项目背景
• 定期执行晨间状态检查

连接运行中的Jupyter，保留变量和已加载数据，反复试验Python代码、检查对象及编辑单元格，并可重启后从上到下验证整个笔记本。

• 保留变量并逐步探索数据
• 检查DataFrame和Python对象
• 试验并修改API调用或复杂代码

帮助将claude-flow v3中职责过多的大型类按功能拆分，整理依赖关系、领域边界和事件协作，支持迁移到便于扩展功能与独立测试业务逻辑的结构。

• 按职责拆分大型类
• 设计任务、会话和监控边界
• 设计插件与事件协作

帮助将claude-flow v3中职责过多的大型类按功能拆分，整理依赖关系、领域边界和事件协作，支持迁移到便于扩展功能与独立测试业务逻辑的结构。

• 按职责拆分大型类
• 设计任务、会话和监控边界
• 设计插件与事件协作

Automate forms, clicks, screenshots, and website checks in a browser where you are already signed in. A separately launched browser also supports scraping and network capture, while login or verification steps can be handed to a person.

中文简介正在准备中。当前显示英语简介。

• Fill forms on websites where you are already signed in
• Capture screenshots and check website behavior
• Record network traffic in a separately launched browser

Analyze CSV, Parquet, and JSON files to answer questions through grouping, joins, cleaning, time series, and charts. Chooses DuckDB or Polars and a suitable processing location based on the task and available memory.

中文简介正在准备中。当前显示英语简介。

• Summarizing and joining data files
• Exploring trends and distributions
• Cleaning data before analysis

Combine laboratory animal welfare measurements into reference-relative RELSA severity scores. Analyze individual trajectories, explore forecasts for specified observation times, and derive candidate score zones, with explicit checks on normalization, reference selection, prediction intervals, and evaluation limits.

中文简介正在准备中。当前显示英语简介。

• Combine animal welfare measurements into daily scores
• Compare group severity using a shared reference
• Explore severity forecasts at specified observation times

Optimize scientific Python workloads for NVIDIA GPUs by choosing suitable libraries and reducing bottlenecks. Compare outputs with the CPU version and measure complete processing time, including data transfers, to determine whether the GPU implementation provides a useful improvement.

中文简介正在准备中。当前显示英语简介。

• Assess whether slow Python processing would benefit from a GPU
• Move NumPy or pandas workloads to suitable GPU libraries
• Validate GPU results against CPU outputs

Analyze how EDR, software that monitors endpoint threats, and antivirus products detect activity. Support authorized exercises by examining monitoring mechanisms, assessing evasion approaches, and checking detection results in an isolated test environment.

中文简介正在准备中。当前显示英语简介。

• Assessing EDR detection coverage in authorized exercises
• Examining internal monitoring mechanisms
• Testing an in-house implant against security products