「gpu」の検索結果

Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU. Covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.

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。

Three.js 性能优化指南。当 Three.js/React Three Fiber 项目出现掉帧、内存增长、加载缓慢、绘制调用过多，或需要迁移 WebGPU、实现大规模粒子/实例化渲染、配置资源压缩管线时使用。触发关键词："Three.js 优化"、"WebGPU"、"draw calls"、"内存泄漏"、"TSL"、"InstancedMesh"、"R3F 优化"等。不用于：通用 React 性能问题（用 vercel-react-best-practices）、WebGL/Three.js 入门教学、3D 美术资产的制作本身。

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。

Build, deploy, debug, or maintain a Hugging Face Space using Gradio, Docker, or Static SDKs. Use for general Space hosting and configuration; use huggingface-zerogpu for ZeroGPU runtime constraints and lora-space-builder for LoRA demos.

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。

Resizes, scales, and adjusts video resolution and dimensions using GPU-accelerated NVENC encoding via Volcengine LAS. Video resizing, video scaling, video upscaling, and video downscaling — change video resolution, enlarge or shrink video dimensions, and adjust video size for different platforms and screens. Video compression by reducing resolution and video transcoding and re-encoding with specific dimension constraints. Supports flexible min/max width and height ranges with aspect ratio preservation strategies (increase, decrease, or disable), including landscape to portrait conversion. Async submit-poll workflow with batch support. Use this skill when the user wants to resize or scale video resolution (upscale/downscale), change video dimensions for different platforms, compress videos by reducing resolution, transcode/re-encode videos with GPU NVENC, adjust aspect ratio including landscape-to-portrait conversion, adapt videos for mobile/web/social media, or batch process multiple videos.

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。

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

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。

Best practices for Docker-based ROS2 development including multi-stage Dockerfiles, docker-compose for multi-container robotic systems, DDS discovery across containers, GPU passthrough for perception, and dev-vs-deploy container patterns. Use this skill when containerizing ROS2 workspaces, setting up docker-compose for robot software stacks, debugging DDS communication between containers, configuring NVIDIA Container Toolkit for GPU workloads, forwarding X11/Wayland for rviz2 and GUI tools, or managing USB device passthrough for cameras and serial devices. Trigger whenever the user mentions Docker with ROS2, docker-compose for robots, Dockerfile for colcon workspaces, container networking for DDS, devcontainer for ROS2, multi-stage builds for ROS2, or deploying ROS2 in containers. Also trigger for CI/CD with Docker-based ROS2 builds, CycloneDDS or FastDDS configuration in containers, or shared memory in Docker. Covers Humble, Jazzy, and Rolling distributions across Ubuntu 22.04 and 24.04 base images.

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。

cuML operating skill for GPU-accelerated classical ML, cuml.accel, Dask multi-GPU workflows, data utilities, and native source-build guidance.

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。

Operate a running Guaardvark: GPU and VRAM state, plugin start/stop, logs, Celery tasks, the Interconnector sync to other machines, overnight RAG autoresearch, and infographics. Use when the user asks what is using the GPU, why a job is stuck, to start or stop ComfyUI/Audio Foundry/Swarm, to sync another box, to run autoresearch, or to make an infographic.

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 the evidence loop of one long-horizon GPU kernel optimization episode. Use this skill to reconstruct the incumbent, profile and localize a bottleneck, research progressively, plan one coherent direction, implement and repair, validate development correctness and performance, and record every decisive experiment in the episode journal.

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。

Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel. Use this skill to understand compute semantics, determine the target platform and framework, search reference implementations, and produce a correct V0 baseline with performance records for later profile-driven optimization.

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。

Patterns for running AI models locally in browsers using WebGPU, Transformers.js, WebLLM, and ONNX Runtime. Zero API costs, full privacy. Use when "on-device AI, browser AI, WebLLM, Transformers.js, WebGPU, edge inference, offline AI, client-side ML, ONNX web, " 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。

Use when building a 3D web game with three.js, Babylon.js or PlayCanvas - render loop and delta per library, fixed-step physics with Rapier or Havok, explicit dispose of GPU resources, instancing and draw-call budgets, glTF with Draco/meshopt/KTX2, pixel ratio and resize, WebGPU opt-in, React Three Fiber notes, and headless testing.

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。

Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.

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 Kolu client-side performance issues (memory leaks, high GPU, slow interactions) using chrome-devtools MCP + the Debug → Diagnostic info dialog + heap-snapshot analyzers. Triggers on "memory leak", "GPU memory", "tab bloat", "why is kolu slow", "debug performance", "zombie canvas", "WebGL leak", or any

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 and configure model serving infrastructure — endpoint scaling, batching, GPU allocation. Use when asked to "serve this model", "design an inference endpoint", or "size GPU allocation for serving".

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。

Build interactive live slide decks with Vite + React 19, TanStack Router, WebGPU shaders, Framer Motion orchestration, 1920x1080, access-gated SPA. 39 components (layout, interaction, graphics, chrome, navigation), direction-aware slide transitions, presenter mode with speaker notes and BroadcastChannel sync, Playwright PNG/PDF export, YAML-driven authoring, Cloudflare/Vercel/Netlify deploy. Triggers on: slide deck, presentation, pitch deck, investor deck, product demo, conference talk, live slides, WebGPU slides, interactive presentation, presenter mode, speaker notes, overwatch deck.

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。

Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, tiling, double-buffering, or CuAssembler hand-tuning).

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 analyzing warp divergence, memory coalescing, shared memory bank conflicts, cache behavior, atomics, or occupancy tradeoffs on NVIDIA and AMD GPUs. Not for tool commands: use cuda-profiling.

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。

Scaffold a new Tip in the ai-product-dev-tips repository following the existing directory/format conventions, and register its link in the root README.md. Use this whenever the user wants to add, create, or write a new Tip in this repo — e.g. "nlp_processing に〜の Tip を追加して", "新しい Tips を作って", "〜の解説 Tip を書いて", "this repo に〜のネタを追加". It picks the right category and next sequential number, matches the README format of nearby Tips, generates code scaffolding (Dockerfile / requirements.txt / *_cpu.sh / *_gpu.sh / *.py) only when the Tip needs runnable code, and inserts the link into the correct <details> section of the root README. Trigger this even if the user doesn't say the word "skill" — any request to add a new entry to this Tips collection should use it.

Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript client patterns

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。

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc 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。

WAV/動画音声を単一パスGPU転写（mlx-whisper）した後、fulltextを意味区切りでN分割しLLM改行だけを並列化してSRT字幕を高速生成する /srt の高速版。日本語トーク動画用。「/srt-fast」で実行。

Expert-level computer architecture covering CPU design, instruction sets, pipelining, cache hierarchy, memory systems, parallel architectures, and GPU computing.

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。

Biblioteca do Facebook para busca eficiente de similaridade e clustering de vetores densos. Suporta bilhões de vetores, aceleração GPU e vários tipos de índice (Flat, IVF, HNSW). Use para busca k-NN rápida, recuperação de vetores em larga escala ou quando você precisa de busca pura de similaridade sem metadados. Melhor para aplicações de alto desempenho.

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。