PyTorch agent skills, page 5

L3 recipe that runs a Torch LLM PTQ end-to-end for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input): quantize → validate → evaluate.

amd/Quark

Route Quark user goals to the correct atomic skill or workflow.

amd/Quark

Route Quark user goals to the correct atomic skill or workflow.

amd/Quark

Guides through installation, configuration, and first-time setup of the Claude Patent Creator system.

RobThePCGuy/Claude-Patent-Creator

Generate C/C++ or CUDA code from an AI model (PyTorch, LiteRT) using MATLAB Coder or GPU Coder.

matlab/matlab-agentic-toolkit

Creates MATLAB interfaces to Python image processing and computer vision models from GitHub repositories or pip-installable packages using MPyReq.

matlab/matlab-agentic-toolkit

Validate Triton-Ascend kernel outputs against PyTorch references with dtype-aware tolerances, exact integer checks, bfloat16 promotion, and boolean handling.

Krusty84/triton-ascend-agent-dev-kit

This skill provides guidance for implementing PyTorch pipeline parallelism for distributed training of large language models.

lazyFrogLOL/Harness_Engineering

This skill provides guidance for implementing tensor parallelism in PyTorch, specifically column-parallel and row-parallel linear layers.

lazyFrogLOL/Harness_Engineering

Installs or verifies AMD Quark and ensures the selected Python environment has an accelerator-matched PyTorch.

amd/Quark

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request…

amd/Quark

Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines.

jaechang-hits/SciAgent-Skills

PyTorch Geometric (PyG) for graph neural networks: node/graph classification, link prediction with GCN, GAT, GraphSAGE, GIN.

jaechang-hits/SciAgent-Skills

Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction…

joshzyj/open-scholar-skill

通过 PyTorch torch.distributed 接口测试昇腾 NPU 通信算子性能。支持指定任意 tensor shape、dtype，使用 torchrun 启动，贴近真实训练场景的通信算子测试与性能分析。Use for testing collective communication operators (AllReduce, AllGather, ReduceScatter…

ascend-ai-coding/awesome-ascend-skills

Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).

majiayu000/claude-skill-registry

A skill your agent uses for NVIDIA NeMo Speech ASR, TTS, audio processing, SpeechLM2 and voice-agent workflows, speaker diarization, data tooling, and repository development.

majiayu000/claude-skill-registry

PyTorch-native Graph Neural Network framework for molecules and proteins.

aipoch/medical-research-skills

Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.

AlexAI-MCP/hermes-CCC

Build a ChatGPT-like LLM from scratch using PyTorch step by step

wentorai/research-plugins

Avoid common PyTorch mistakes and apply robust training patterns

wentorai/research-plugins

PyTorch Lightning framework for scalable model training and research

wentorai/research-plugins

GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.

Mathews-Tom/armory

A skill your agent uses when selecting Sentence Transformers inference backends or exporting/optimizing models for PyTorch, ONNX, or OpenVINO.

VectorSpaceLab/AREX-Skill

Use this sub-skill for Torch-TensorRT model compilation, dynamic input planning, torch.export workflows, save/load formats, raw TensorRT engines, and compile-time troubleshooting.

VectorSpaceLab/AREX-Skill

Use this sub-skill when constructing torchvision datasets, validating dataset roots and downloads, wrapping datasets for transforms v2, decoding or encoding images with torchvision.io, or using…

VectorSpaceLab/AREX-Skill

A skill your agent uses when running RobustVideoMatting inference, loading weights, using convertvideo or TorchHub, converting image/video inputs, or reasoning about exported model runtimes.

VectorSpaceLab/AREX-Skill

A skill your agent uses when working with RobustVideoMatting MattingNetwork APIs, recurrent states, model variants, refiners, tensor shapes, and safe synthetic forward checks.

VectorSpaceLab/AREX-Skill

Use torchsummary.summary and torchsummary.summarystring to inspect PyTorch nn.Module shapes, parameter counts, devices, dtypes, and memory estimates.

VectorSpaceLab/AREX-Skill

Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting.

VectorSpaceLab/AREX-Skill

A skill your agent uses for PaddleViT's DINO self-supervised vision-transformer pretraining, multi-crop data contracts, teacher/student configuration, single- or multi-GPU launch planning…

VectorSpaceLab/AREX-Skill

Use Torch Points3D for point-cloud deep learning APIs, datasets/transforms, Hydra training/evaluation, checkpoints, sparse backend decisions, and registration workflows.

VectorSpaceLab/AREX-Skill

A skill your agent uses for Torch-TensorRT tasks: compiling PyTorch models with TensorRT, dynamic-shape/export workflows, runtime optimization, Triton/C++/distributed deployment, debugging…

VectorSpaceLab/AREX-Skill

Use TorchMetrics to choose, inspect, and combine metric families for PyTorch evaluation, including core API, domain metrics, model-based metrics, and wrappers.

VectorSpaceLab/AREX-Skill

A skill your agent uses when working with TorchVision models, weights, transforms, TVTensors, datasets, image IO, visualization utilities, vision ops, detection helpers, or official reference…

VectorSpaceLab/AREX-Skill

Use Towhee's optional PyTorch Trainer, TrainingConfig YAML, NNOperator training bridge, and towhee.models package boundaries safely.

VectorSpaceLab/AREX-Skill

A skill your agent uses when planning or auditing TorchVision reference training/evaluation workflows for classification, quantization, detection, segmentation, video classification, optical flow…

VectorSpaceLab/AREX-Skill

Guide safe video-file, webcam, and optional half-precision demo use for pytorch-yolo-v3.

VectorSpaceLab/AREX-Skill

A skill your agent uses for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.

VectorSpaceLab/AREX-Skill

Ankh 蛋白质语言模型昇腾 NPU 迁移 Skill，适用于 Ankh base/large、Ankh3 large/XL 以及同类基于 HuggingFace Transformers 与 PyTorch 的蛋白模型从 CUDA/GPU 到华为 Ascend NPU 的环境检查、代码适配、权重加载、验证脚本补齐与文档沉淀。

ascend-ai-coding/awesome-ascend-skills

昇腾 TensorFlow Community 迁移适配 Skill，适用于将基于 TensorFlow 2.x 的模型原生部署到华为 Ascend NPU，而不经过 TF 到 PyTorch 转换，覆盖 aarch64 源码编译 TF 2.6.5、tfplugin 安装、自动迁移工具使用、手动适配与精度验证。

ascend-ai-coding/awesome-ascend-skills

DeepFRI 的 TensorFlow 到 PyTorch 转换与昇腾 NPU 迁移 Skill，适用于蛋白质功能预测场景下的 TF 模型分析、PyTorch 重写、权重逐层映射、NPU 推理与精度验证，尤其适合需要在 Ascend 上运行 DeepFRI CNN 或 GCN 路径时使用。

ascend-ai-coding/awesome-ascend-skills

DeepFRI TensorFlow 原生昇腾 NPU 迁移 Skill，适用于不做 TF 到 PyTorch 转换、而是直接使用 TensorFlow 2.6.5 与 npudevice 在华为 Ascend 上运行 DeepFRI 的场景，覆盖源码编译、tfplugin 安装、代码适配、推理与 CPU 对比验证。

ascend-ai-coding/awesome-ascend-skills

OligoFormer 昇腾 NPU 迁移 Skill，适用于将基于 PyTorch Transformer 的 siRNA 效能预测模型迁移到华为 Ascend NPU，覆盖环境搭建、RNA-FM 依赖安装、代码适配、推理验证与可选训练流程。

ascend-ai-coding/awesome-ascend-skills

ProteinBERT 昇腾 NPU 部署与迁移 Skill，适用于将 TensorFlow 或 Keras 版 ProteinBERT 转成基于 PyTorch 与 torchnpu 的实现，覆盖权重转换、embedding 提取、微调训练、注意力可视化和 GPU 与 NPU 精度验证。

ascend-ai-coding/awesome-ascend-skills

TensorFlow 或 Keras 模型改写到 PyTorch 的通用 Skill，适用于在华为 Ascend NPU 或其他依赖 PyTorch 生态的平台上完成层级映射、权重转换、逐层数值验证和端到端精度对比，尤其适合 ProteinBERT、DeepFRI 这类科学模型的跨框架迁移。

ascend-ai-coding/awesome-ascend-skills

HuggingFace Diffusers 环境配置指南，用于华为昇腾 NPU。覆盖 CANN 版本检测、PyTorch + torchnpu 安装、Diffusers 库安装及环境验证。当用户需要在昇腾 NPU 上配置 Diffusers 环境时使用。

ascend-ai-coding/awesome-ascend-skills

基于 PyTorch 框架的昇腾 NPU 模型推理融合算子优化技能。分析模型代码，识别可替换为 torchnpu 融合算子的计算模式，生成替换方案。触发场景：torchnpu 融合算子替换、MoE/Attention/FFN/Norm 等模块的推理算子适配、torchnpu API 使用咨询。基于仓库已有模型的融合算子经验，按计算语义推荐最佳方案。

ascend-ai-coding/awesome-ascend-skills