# openai/blocksparse

Efficient GPU kernels for block-sparse matrix multiplication and convolution

Repository: https://github.com/openai/blocksparse
Canonical: https://ross.abutalabs.com/products/blocksparse
Homepage: https://blog.openai.com/block-sparse-gpu-kernels/
Language: Cuda
License: MIT
License Family: permissive
Archived: true
Last push: 2023-06-08T11:01:25+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3192, "days_push": 1182, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1068, forks 198 (observed 2026-08-28T04:03:27.516789+00:00)

## What it is
A Python package of TensorFlow ops and custom CUDA GPU kernels for block-sparse matrix multiplication and convolution, plus related ops like edge bias and sparse weight/layer norm. Developed by OpenAI to accelerate sparse neural network training on Nvidia GPUs.

## Use cases
- speed up training of sparse neural networks on gpu
- block-sparse matrix multiplication in tensorflow
- train large language models with sparse weights
- block-sparse convolution kernels for cuda
- reduce gpu compute cost of dense matmul via sparsity

## When to choose
- you use TensorFlow 1.x on Linux with an Nvidia Pascal/Maxwell GPU and want block-sparse ops
- you need fast custom CUDA kernels for sparse matmul or convolution
- you're reproducing OpenAI's block-sparse GPU kernel research

## When to avoid
- you use modern frameworks like PyTorch or TensorFlow 2.x
- you need cross-platform or Windows/macOS support
- you want a maintained library - it targets old CUDA/TensorFlow versions and sees little activity

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, gpu-computing, deep-learning
- domain: machine-learning, deep-learning, gpu-computing
- platform: python
- tags: cuda-kernels, block-sparse, sparse-matmul, tensorflow-ops, sparse-convolution, linux, gpu

## Member repositories
- openai/blocksparse (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:27.516789+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 2026-08-30T06:54:44.638597+00:00, confidence not recorded.
  - readme: https://github.com/openai/blocksparse (fetched 2026-08-28T04:03:27.516789+00:00, sha 2acd55851a64)
- Data as of 2026-08-30T08:39:29.467469+00:00.