PyTorch skills

stas00/ml-engineering

Skill Claude CodeCodex

This file moved to skills/ml-engineering/SKILL.md.

NVIDIA/TensorRT-LLM

Skill Claude Code ✓ vendor

Launch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill) sizing the headroom the…

flashinfer-ai/flashinfer

Skill Claude CodeCodex needs its repo

Use this guide when importing a new kernel-team drop or adapting FlashInfer to changes in that drop. VENDOR.md records the pinned source and export exceptions; TUNING.md covers tuning and measurements.

NVIDIA/physicsnemo

Skill Claude CodeCodex ✓ vendor

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 register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…

stas00/the-art-of-debugging

Skill Claude CodeCodex

Systematic methodology and concrete tool recipes for debugging Unix, Python, and PyTorch programs - crashes, hangs, segfaults, wrong output, CUDA OOM, NaN/Inf, slowness, and multi-node/multi-GPU issues. Use when a program crashes, hangs, deadlocks, segfaults, runs out of memory (OOM), produces NaN/Inf or wrong…

PharMolix/OpenBioMed

Skill Claude CodeCodex

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…

NVIDIA/TensorRT-Model-Connect

Skill Codex needs its repo ✓ vendor

Review a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, and exact-head validation evidence. Use for contributor self-review before marking a PR ready, or when deciding whether a community PR is…

graphsignal/graphsignal-profiler

Skill Claude CodeCodex

Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.

Ascend/agent-skills

Skill Claude CodeCodex

Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full…