AI & LLM Engineering · PyTorch · For data scientists

Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

pytorch/pytorch

Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses when adding a new PyTorch model to Pyrefly's shape-tracking example corpus under tensor-shapes/pyrefly-torch-stubs/examples — i.e.

facebook/pyrefly

Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

stas00/the-art-of-debugging

Manage CI for PyTorch ghstack stacks by running CI where its results are useful now and deferring other PRs with [no-ci].

pytorch/pytorch

Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.

open-infra-skills/infra-skills

Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)

SharpAI/DeepCamera

Port a PyTorch model to use pyrefly's tensor shape type system (Tensor[[B, C, H, W]], Int[T]).

facebook/pyrefly

Answers ExecuTorch questions from a local wiki on backends, export pitfalls, quantization recipes, runtime errors and SoC compatibility.

pytorch/executorch

Routes agents to the right tangermeme reference for analyzing trained genomic deep learning models, from attributions and motif experiments to variant effects and design.

jmschrei/tangermeme

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab).

wanshuiyin/ARIS-in-AI-Offer

Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

Orchestra-Research/AI-Research-SKILLs

Refresh GitNexus indexing and regenerate local GitNexus skills when repository status is stale.

ML4ITS/TimeVQVAE

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

sablin39/tilelang-cuda-skills

Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading.

wanshuiyin/ARIS-in-AI-Offer

Guides an agent through tracking ML experiments with W&B: run logging, config capture, hyperparameter sweeps, artifacts and a model registry.

Orchestra-Research/AI-Research-SKILLs

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.

JimLiu/science-skills

Guides users through selecting, configuring, or creating a PyTorch model for a PINA problem.

PINA-org/PINA

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction.

Orchestra-Research/AI-Research-SKILLs

Produces ranked, evidence-grounded next steps when an ML experiment has stalled, drawing on a Leeroopedia knowledge base or on fetched docs and issues.

Leeroo-AI/superml

Run AlphaGenome-PyTorch to get genomic track predictions — via the agt predict CLI (single locus, BED regions, whole chromosomes, raw FASTA sequences, or per-gene count tables/AnnData), variant…

genomicsxai/alphagenome-pytorch

Adds distributed and mixed-precision training to a PyTorch script with a few Accelerate lines, then launches it on one GPU, many GPUs or DeepSpeed and FSDP setups.

Orchestra-Research/AI-Research-SKILLs

Build and debug cuEquivariance irreps, custom Irrep subclasses, Clebsch-Gordan tensor products, and equivariant or segmented polynomials.

NVIDIA-BioNeMo/bionemo-agent-toolkit

Uses Ray Data to read, transform and write large datasets across a cluster for ML training and batch inference, with streaming execution and optional GPU steps.

Orchestra-Research/AI-Research-SKILLs

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab).

wanshuiyin/Auto-claude-code-research-in-sleep

Checks training code, configs and math against documented framework behavior before an expensive run, citing a knowledge base or official docs for every claim.

Leeroo-AI/superml

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

amd/Quark

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.

Orchestra-Research/AI-Research-SKILLs

Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works.

Orchestra-Research/AI-Research-SKILLs

Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

Orchestra-Research/AI-Research-SKILLs

Generates text embeddings locally with the sentence-transformers library for RAG, semantic search, clustering and similarity, with model picks for general, multilingual and legal text.

Orchestra-Research/AI-Research-SKILLs

Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs.

Orchestra-Research/AI-Research-SKILLs

Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.

pytorch/executorch

Organizes PyTorch training code into LightningModules, DataModules and Trainers, with multi-GPU strategies, callbacks and logging configured.

davila7/claude-code-templates

Explains machine learning predictions with SHAP: picking the right explainer, computing Shapley values and drawing waterfall, beeswarm, bar and force plots.

davila7/claude-code-templates

Covers logging and viewing training metrics, histograms, model graphs, embeddings and profiles with TensorBoard in PyTorch and TensorFlow projects.

Orchestra-Research/AI-Research-SKILLs

Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.

pytorch/test-infra

Publish a Python package to PyPI using uv with credentials loaded from a local .secrets file.

ML4ITS/TimeVQVAE

Guide to using Mamba selective state-space models for linear-time sequence modeling, from the Mamba block and pretrained checkpoints to Mamba-2 and speed comparisons.

Orchestra-Research/AI-Research-SKILLs

Walks through nanoGPT, Karpathy's compact GPT implementation: training on Shakespeare, reproducing GPT-2, fine-tuning GPT-2 checkpoints and training on your own text.

Orchestra-Research/AI-Research-SKILLs

Explains RWKV, a hybrid that trains in parallel like a GPT and runs inference like an RNN with constant memory per token, plus usage, fine-tuning and troubleshooting.

Orchestra-Research/AI-Research-SKILLs

Graph Neural Networks (PyG). An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

affaan-m/ECC

PyTorch training reference: architecture choice by data type, scaling rules, a training loop, optimizer and learning-rate choices, and fixes for loss spikes or OOM.

Orchestra-Research/AI-Research-SKILLs

Guide to renting GPUs on Lambda Labs for ML training and inference: on-demand instances, 1-Click Clusters, SSH access, persistent filesystems and alternatives.

Orchestra-Research/AI-Research-SKILLs

Adds PyTorch FSDP2 (fullyshard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing.

Orchestra-Research/AI-Research-SKILLs

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks.

davila7/claude-code-templates

Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel.

alibaba/atrex-kernel-agent