AI & LLM Engineering · PyTorch

A skill your agent uses when writing or debugging nvMolKit Python code for GPU-accelerated RDKit fingerprints, similarity, conformers, clustering, and molecular searches.

NVIDIA/skills

A skill your agent uses when you need a runnable PyTorch training repo for a medical-imaging task (segmentation, classification, detection, synthesis, self-supervised, or fine-tuning a pretrained…

Aperivue/medsci-skills

Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving.

llama-farm/llamafarm

Review vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer.

pytorch/test-infra

Build and debug masked one-dimensional elementwise kernels for Triton-Ascend, including launch wrappers and PyTorch/NPU correctness checks.

Krusty84/triton-ascend-agent-dev-kit

Run PyTorch training across GPUs with minimal changes. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Speed up long-sequence transformer training and inference. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Fully sharded data-parallel training for large models. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Pretrain LLMs at scale with PyTorch 4D parallelism. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation, and job export; use when the user names…

NVIDIA/skills

Fallback loader for the canonical PyTorch ci-metrics skill. An agent skill from pytorch/test-infra.

pytorch/test-infra

Train ML models on Databricks. An agent skill from databricks/databricks-agent-skills.

databricks/databricks-agent-skills

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse…

NVIDIA/skills

Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and…

NVIDIA/skills

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.

NVIDIA/skills

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches.

NVIDIA/skills

InternVideo2-CLIP L14 (TAO videoclip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment.

NVIDIA/skills

PyTorch-based TAO image classification. An agent skill from NVIDIA/skills.

NVIDIA/skills

Apply existing ShapeShifter graph passes to an .onnx model via the quark-cli shapeshifter CLI or a ShapeShifter YAML.

amd/Quark

Diagnose failed Quark installation, PTQ execution, script generation, or export attempts.

amd/Quark

Install or verify the correct PyTorch build for a user's accelerator backend before Quark installation.

amd/Quark

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

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

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

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

Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use only when the request names…

NVIDIA/skills

Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use when the user names plain PyTorch or…

NVIDIA/skills

Extract Intel GPU ISA (assembly) from any XPU kernel. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops

A skill your agent uses when asked to implement a fix for a root-caused failure, apply a proposed patch, or produce a staged code change from triage output.

intel/torch-xpu-ops

A skill your agent uses when asked to verify a fix works, confirm a staged patch resolves a failure, or produce a before/after summary of a fix.

intel/torch-xpu-ops

A skill your agent uses when setting up a new torch-xpu-ops release branch corresponding to a PyTorch release.

intel/torch-xpu-ops

Build PyTorch from source with Intel XPU (GPU) support. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops

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

Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend.

jinzhezenggroup/computational-chemistry-agent-skills

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

NVIDIA/skills

Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA.

intel/torch-xpu-ops

Find upstream PyTorch behavior or fixes that may require XPU parity work, validate them on XPU, and produce independently reviewed evidence.

intel/torch-xpu-ops

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

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

jaechang-hits/SciAgent-Skills

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

A skill your agent uses when asked to reproduce a bug, verify a nightly CI failure, or confirm a failure still exists on latest source.

intel/torch-xpu-ops

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供…

majiayu000/spellbook