# rusty1s/pytorch_scatter

PyTorch Extension Library of Optimized Scatter Operations

Repository: https://github.com/rusty1s/pytorch_scatter
Canonical: https://ross.abutalabs.com/products/pytorch_scatter
Homepage: https://pytorch-scatter.readthedocs.io
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, scatter, segment, gather
Last push: 2026-06-03T00:51:47+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 8, longevity 100
- inputs: {"age_days": 3182, "days_push": 92, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1745, forks 207 (observed 2026-08-28T04:05:30.712365+00:00)

## What it is
A PyTorch extension library providing highly optimized scatter and segment (sparse update) operations with sum, mean, min, and max reductions. It supports CPU and GPU with backward implementations, composite functions like scatter_softmax, and pip wheels for major OS/PyTorch/CUDA combinations.

## Use cases
- aggregate tensor values by group index in PyTorch
- perform segment reductions on sorted or CSR-compressed indices
- compute scatter softmax or logsumexp over groups
- speed up graph neural network message aggregation on GPU
- implement sparse update operations missing from core PyTorch

## When to choose
- you need fast scatter/segment reductions in PyTorch on CPU or GPU
- you're building GNNs or point cloud models requiring grouped aggregation
- you need differentiable, traceable scatter operations with CUDA support

## When to avoid
- you use TensorFlow, JAX, or another framework instead of PyTorch
- your reduction needs are simple enough for built-in torch index ops
- you cannot install CUDA-matched wheels in your environment

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, gpu-computing, math
- domain: machine-learning, deep-learning, gpu-computing
- platform: python, windows
- tags: pytorch, scatter-operations, segment-operations, sparse-update, cuda, tensor-operations, linux, macos, gpu

## Member repositories
- rusty1s/pytorch_scatter (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:30.712365+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:29:17.072971+00:00, confidence not recorded.
  - readme: https://github.com/rusty1s/pytorch_scatter (fetched 2026-08-28T04:05:30.712365+00:00, sha 4d8fa81c11a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.