564 件 ・ 関連度順
概要と使いどころ
Orquestração multi-nuvem para workloads de ML com otimização automática de custos. Use quando precisar executar treinamento ou jobs em lote em múltiplas nuvens, aproveitar instâncias spot com auto-recuperação ou otimizar custos de GPU entre provedores.
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。
Formato GGUF e quantização llama.cpp para inferência eficiente em CPU/GPU. Use ao implantar modelos em hardware de consumidor, Apple Silicon, ou quando precisar de quantização flexível de 2-8 bits sem requisitos de GPU.
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。
Quantização pós-treinamento em 4-bits para LLMs com perda mínima de precisão. Use para implantar modelos grandes (70B, 405B) em GPUs de consumo, quando você precisa de redução de memória 4× com <2% de degradação de perplexidade, ou para inferência mais rápida (aceleração de 3-4×) vs FP16. Integra com transformers e PEFT para fine-tuning QLoRA.
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。
Integrate a GPU operator into ATREX with minimal source, compatible lazy APIs, hardware dispatch, atrex-prefixed kernels, one functional test file, and target-GPU validation.
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。
吉里吉里Z (kirikiri Z) 本体クラス API のリファレンス。TJS2 で吉里吉里Z 上のスクリプトを書く、レビューする、デバッグするときに使う。Layer / Window / Bitmap / System / Storages / Font / Plugins / Timer / Debug / AsyncTrigger / Scripts / BinaryStream / Matrix32 / Matrix44 / Rect / ImageFunction のコア API、サウンド系 (WaveSoundBuffer / SoundBuffer / VideoOverlay)、DrawDevice (BasicDrawDevice / SDLDrawDevice / OGLDrawDevice / GPUDrawDevice / NullDrawDevice)、OpenGL 描画系 (Canvas / Texture / ShaderProgram / Offscreen / VertexBinder / VertexBuffer)、および主要プラグイン提供クラス (HttpRequest / GdiPlus.* / WIN32Dialog / CSVParser / LineParser / Process / Pad / MenuItem / Unzip / Zip / PSD / SimpleHTTPServer) を網羅。**呼び出されたら必ず「共通パターン」と「クロスカッティング概念」を確認し、必要な詳細クラスは doc/reference/*.md を Read しに行くこと。** TJS2 言語そのものや組み込みクラス (Array / Dictionary / Math 等) は別 skill (`tjs2`) を参照。エンジン内部構造 (C++ 実装、レンダリングパイプライン詳細) は対象外。
Cold start — every GPU, every model size GPU Model ZSE vLLM Speedup NVIDIA T4 (16 GB) Qwen2.
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。
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
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 model validation and benchmarking. Investigates any ML model (LLM, image gen, TTS, time series, etc.), runs it on GPU cloud, evaluates quality and performance, and generates HTML reports. Use when user asks to verify, benchmark, evaluate, or test a model. Triggers on "verify model", "benchmark", "evaluate model", "test model", "run benchmark", "model evaluation", "モデルを検証", "ベンチマーク", "モデルを試して".
Rust 製ローカルファースト vector 特化クエリ DB fandhe-db (PostgreSQL wire protocol v3 互換) の fandhe-vector-db-engine / fandhe-vector-db-wire-server リファレンス。 USING PLAN / USING OPERATION_ID 構文、precision・recall モード、 HNSW / BM25 転置索引 / RRF hybrid / rerank、redb 永続化、 tenant・RLS、SIMD / wgpu カーネル、wire_code エラー契約。
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-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。
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。
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
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。
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
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。
Rive アニメーションランタイムリファレンス。 Rive クラス、useRive、useStateMachineInput、RiveComponent、 State Machine、Data Binding、ViewModel、ViewModelInstance、Events、 Layout / Fit / Alignment、.riv ファイル読み込み。 @rive-app/canvas、@rive-app/webgl2、@rive-app/react-canvas、@rive-app/react-webgl2。 Rive Scripting API (Luau)、Artboard、Property、Path / Paint / Renderer、 WGSL Shaders、GPU pipeline、Node / Layout / Converter スクリプト。
AMD ROCm / HIP GPU コンピューティングリファレンス。 hipMalloc, hipLaunchKernelGGL, HIP Graph, HIPRTC, hipify, rocBLAS, MIOpen, RCCL, rocprofv3, amd-smi, rocminfo, CDNA1-4 / RDNA1-4, MI300 / MI350, gfx942, Matrix Core, wave32/64。
Blender Python API リファレンス。bpy / bmesh / mathutils / gpu / bpy_extras モジュール、 bpy.data / bpy.context / bpy.ops / bpy.types / bpy.props コア API。 Mesh / Modifier / Geometry Nodes / Armature / Keyframe / Driver / Shape Key / NLA、 Cycles / EEVEE / Shader Nodes / Rigid Body / Cloth / Fluid / Compositor Nodes / AOV、 headless CLI レンダリング、add-on 開発、Extensions システム、MCP Server (Model Context Protocol)。
Check whether a Playwright, Puppeteer, Selenium or CDP-driven browser presents a coherent fingerprint, using liarjs as a library against a Page you already have - navigator.webdriver, HeadlessChrome tokens, worker versus main-thread identity, patched-API integrity, WebGL versus WebGPU GPU identity. Use when asked whether an automated browser looks like a normal one, when a headless setup or a stealth plugin's effect needs measuring rather than assuming, or when an assertion on fingerprint quality belongs in a test suite.
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。
Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e observabilidade de modelo. Use quando o usuário disser "GPU", "MCP server", "LLM", "inferência", "modelo", "gateway de IA", "custo de token", "rate limit da API de IA", "self-host de modelo".
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。
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw sandbox hardening, container security, docker capabilities, process limits, nemoclaw telegram, telegram bot openclaw agent, openshell channel messaging.
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。
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
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。
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
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。
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
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。
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
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。