Implementação educacional do GPT em ~300 linhas. Reproduz o GPT-2 (124M) em OpenWebText. Código limpo e hackeável para aprender transformers. Por Andrej Karpathy. Perfeito para entender a arquitetura do GPT do zero. Treine em Shakespeare (CPU) ou OpenWebText (multi-GPU).
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Serve LLMs com alta throughput usando PagedAttention do vLLM e continuous batching. Use ao fazer deploy de APIs LLM em produção, otimizar latência/throughput de inferência, ou servir modelos com memória GPU limitada. Suporta endpoints compatíveis com OpenAI, quantização (GPTQ/AWQ/FP8) e tensor parallelism.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Fornece treinamento distribuído de LLM nativo do PyTorch usando torchtitan com paralelismo 4D (FSDP2, TP, PP, CP). Use para fazer pré-treinamento de Llama 3.1, DeepSeek V3 ou modelos customizados em escala de 8 a 512+ GPUs com Float8, torch.compile e checkpoint distribuído.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Geração estruturada rápida e serving para LLMs com RadixAttention para cache de prefixos. Use para saídas JSON/regex, decodificação restrita, workflows com agentes que fazem chamadas de ferramentas, ou quando você precisa de 5× mais rápido que vLLM com compartilhamento de prefixos. Alimenta 300.000+ GPUs na xAI, AMD, NVIDIA e LinkedIn.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Fornece orientação para interpretar e manipular internals de redes neurais usando nnsight com execução remota NDIF opcional. Use quando precisar executar experimentos de interpretabilidade em modelos massivos (70B+) sem recursos locais de GPU, ou ao trabalhar com qualquer arquitetura PyTorch.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Ajuste fino com eficiência de parâmetros para LLMs usando LoRA, QLoRA e 25+ métodos. Use ao fazer fine-tuning de modelos grandes (7B-70B) com memória GPU limitada, quando precisa treinar <1% dos parâmetros com perda mínima de precisão, ou para serviços multi-adapter. Biblioteca oficial do HuggingFace integrada ao ecossistema transformers.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
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。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Quantização de pesos consciente da ativação para compressão de LLM de 4-bit com aceleração 3x e perda mínima de acurácia. Use ao implantar modelos grandes (7B-70B) em memória GPU limitada, quando precisa de inferência mais rápida que GPTQ com melhor preservação de acurácia, ou para modelos com instruções ajustadas e multimodais. Vencedor do Prêmio Melhor Artigo MLSys 2024.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Processamento escalável de dados para workloads de ML. Execução em streaming em CPU/GPU, suporta Parquet/CSV/JSON/imagens. Integra-se com Ray Train, PyTorch, TensorFlow. Escala de uma única máquina para centenas de nós. Use para inferência em lote, pré-processamento de dados, carregamento de dados multi-modal ou pipelines distribuídos de ETL.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
Treina modelos de linguagem grandes (2B-462B de parâmetros) usando NVIDIA Megatron-Core com estratégias avançadas de paralelismo. Use ao treinar modelos >1B de parâmetros, precisar de máxima eficiência de GPU (47% MFU em H100), ou necessitar de paralelismo tensor/pipeline/sequência/contexto/expert. Framework pronto para produção usado em Nemotron, LLaMA, DeepSeek.
中文简介正在准备中。当前显示原文说明。
artubss/SKILLS-CLAUDE-CODE☆ 112026年5月17日 更新
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.
中文简介正在准备中。当前显示原文说明。
EthanYoQ/Skill-hub☆ 112026年10月19日 更新
What every Ollama timing field means and the arithmetic that turns it into a claim - tokens per second, time-to-first-token, why total_duration is not latency, why a second run is faster, what changes with context length, quantization, GPU offload and parallel requests - plus the reporting rules that make a benchmark a measurement instead of an anecdote.
中文简介正在准备中。当前显示原文说明。
vecnode/vn-code☆ 102026年10月20日 更新
Use when working with Slang shaders, shader modules, HLSL-compatible GPU code, graphics pipelines, compute shaders, tessellation, ray tracing, parameter blocks, generics, interfaces, capabilities, cross-compilation, shader optimization, shader review, or C++ engine integration for Slang. Trigger on any mention of Slang, .slang files, slangc, SPIR-V from Slang, Slang modules, [shader("compute")], [shader("vertex")], or requests to write/review/refactor shader code with modern language features. Also trigger for Slang-to-HLSL/GLSL/Metal/CUDA cross-compile questions, or when the user says "shader" alongside "generics", "interfaces", "parameter blocks", "autodiff", or "capabilities".
中文简介正在准备中。当前显示原文说明。
mouadja02/skills☆ 102026年10月17日 更新
Set up and optimize a complete local AI infrastructure — Ollama, Open WebUI, local RAG pipelines, and private model serving. Use when running models locally for privacy, compliance, offline use, or cost, or setting up GPU-accelerated local inference and RAG.
中文简介正在准备中。当前显示原文说明。
mouadja02/skills☆ 102026年10月17日 更新
Distributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DISTRIBUTE BY + SET scripts + BucketFS), per-entity federated training with partial_fit and ctx.reset(), batch inference, map-reduce ensemble training, distributed ensemble and SON algorithm for frequent itemset mining (Apriori, FP-Growth, association rules, market-basket analysis), Lua execute script orchestration for iterative algorithms (k-means, SGD, gradient descent), scikit-learn model training, parallel hyperparameter search, per-entity forecasting, anomaly detection, model lifecycle in BucketFS (pickle/joblib/ONNX versioning), GPU acceleration via CUDA SLCs (PyTorch/TensorFlow/RAPIDS), and ML-specific performance tuning (skew, OOM, multi-pass chunking).
中文简介正在准备中。当前显示原文说明。
exasol-labs/exasol-agent-skills☆ 102026年10月14日 更新
Exasol User Defined Functions (UDFs) and Script Language Containers (SLCs). Covers `CREATE SCRIPT`, SCALAR and SET functions, variadic scripts with `EMITS(...)` and `default_output_columns`, the `ExaIterator` and `ExaMetadata` APIs, Python, Java, Lua, and R scripts, Lua execute scripts and `pquery`, BucketFS file access, GPU-accelerated UDFs, `ALTER SESSION SET SCRIPT_LANGUAGES` activation, and building custom Script Language Containers with `exaslct`, `exaslpm`, and `packages.yml`.
中文简介正在准备中。当前显示原文说明。
exasol-labs/exasol-agent-skills☆ 102026年10月14日 更新
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS"...
中文简介正在准备中。当前显示原文说明。
JantonioFC/skillsbank☆ 92026年8月4日 更新
Cut background heat and noise on this machine: audit scheduled tasks by runs per hour, autostart entries, GPU holders, power plan and top CPU, then propose disable or stretch candidates, decide line by line with the operator and apply only approved lines. Triggers: /deflate, fan is loud, laptop runs hot, what can I turn off, machine slow from background load.
中文简介正在准备中。当前显示原文说明。
tonydzi/second-brain-starter-kit☆ 92026年10月20日 更新
Onboard a new machine as a receive-only follower on a multi-machine agent network: it reads the shared vault, canon, skills and memory, runs nothing heavy locally (no RAG, reindex or GPU), and never receives executable hooks from the hub. Checklist-driven, with a verify step at each stage. Triggers: "/follower-onboard <machine>".
中文简介正在准备中。当前显示原文说明。
tonydzi/second-brain-starter-kit☆ 92026年10月20日 更新
August 16, 2026 12 min read Nvidia AI Infrastructure GPUs FinOps Wall Street Nvidia $500B AI Compu
中文简介正在准备中。当前显示原文说明。
openamer/openamer☆ 82026年10月20日 更新
MegaTrain Full Precision Training of 100B+ Parameter LLMs on a Single GPU A RAM-centric architecture that stores parameters in host memory and treats
中文简介正在准备中。当前显示原文说明。
openamer/openamer☆ 82026年10月20日 更新
It took several weeks and dozens of GPUs to train the model on 40 years of historical weather data from the MERRA-2 is NASA’s harmonized dataset of sa
中文简介正在准备中。当前显示原文说明。
openamer/openamer☆ 82026年10月20日 更新
Use when the design concept calls for Three.js or React Three Fiber 3D, WebGL/WebGPU, Rive, Spline, Theatre.js, SVG, canvas, shaders, particle systems, or other immersive creative-web techniques.
中文简介正在准备中。当前显示原文说明。
Lrinvl1203/world-class-web-design-os☆ 82026年10月2日 更新
Use when the user provides a URL from AMD / ROCm official sources (github.com/AMD/*, github.com/ROCm/*, github.com/ROCmSoftwarePlatform/*, rocm.docs.amd.com, amd.com/…/rocm, gpuopen.com). Prefer this over generic GitHub for official ROCm URLs. Generates a hands-on tutorial-following project with no collaborator roles — only the user and the Instructor.
中文简介正在准备中。当前显示原文说明。
THU-MAIC/OpenMAIC-Project☆ 72026年6月26日 更新