assoc-scan

A minimal Pytorch implementation of an associative scan, with support for accelerated backends.

Install

$ pip install assoc-scan

Usage

import torch
from assoc_scan import AssocScan

scan = AssocScan()

gates = torch.randn(1, 1024, 512).sigmoid()
inputs = torch.randn(1, 1024, 512)

out = scan(gates, inputs) # (1, 1024, 512)

To use the accelerated version, simply pass use_accelerated = True and ensure accelerated-scan is installed.

scan = AssocScan(use_accelerated = True)

out = scan(gates, inputs)

Citations

@software{Kyrylov_Accelerated_Scan_2024,
    author    = {Kyrylov, Volodymyr},
    doi       = {10.5281/zenodo.10600962},
    month     = {jan},
    title     = {{Accelerated Scan}},
    version   = {0.1.2},
    year      = {2024}
}

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

assoc_scan-0.0.5.tar.gz (5.5 kB view details)

Uploaded Jul 30, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

assoc_scan-0.0.5-py3-none-any.whl (5.9 kB view details)

Uploaded Jul 30, 2026 Python 3

File details

Details for the file assoc_scan-0.0.5.tar.gz.

File metadata

Download URL: assoc_scan-0.0.5.tar.gz
Upload date: Jul 30, 2026
Size: 5.5 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.8.17

File hashes

Hashes for assoc_scan-0.0.5.tar.gz
Algorithm	Hash digest
SHA256	`84b45d282f0c23dafaf61053f04096a7299020566be8b1178aa5dbb1514c1936`
MD5	`61b8e24445bbef8172162fbbc6bfdd20`
BLAKE2b-256	`996c66cbeb822e06390c56aefca7f1064a6f9a7b38ef68a252325f367e0e9d5f`

See more details on using hashes here.

File details

Details for the file assoc_scan-0.0.5-py3-none-any.whl.

File metadata

Download URL: assoc_scan-0.0.5-py3-none-any.whl
Upload date: Jul 30, 2026
Size: 5.9 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.8.17

File hashes

Hashes for assoc_scan-0.0.5-py3-none-any.whl
Algorithm	Hash digest
SHA256	`48af250daed2c093f4d9ff5d0d28196a9df9756a65f0e6077463f10d72613364`
MD5	`eccd1f0d6bb21c56b8c284b698ae03b8`
BLAKE2b-256	`440a2236f75e84942fff3dba404797f61f7aa935153d568c7ae77af7f21e1b72`