Sign in

asappresearch / sru

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

Stars
2,110 stars
Forks
305 forks
Language
Python
License
MIT
Created
Aug 28, 2017
Last push
Jan 4, 2022
Updated
Nov 2, 2026
Why these Tags: an agent read the README and quoted it
  • Paper implementation from the readme: SRU is a recurrent unit that can run over 10 times faster than cuDNN LSTM, without loss of accuracy tested on many tasks.

An agent gave these Tags from the fixed Tag list in the AwesomeRepos source code. A code check kept each Tag only when its quote is in the text. A wrong Tag? Report an error with the form at the end of this page.

Admitted to the Repository Index on Nov 12, 2026: 2,110 stars on 2026-11-12.

Star History

109 days recorded, Jul 28, 2026 – Nov 13, 2026 (UTC). Net change +8 stars.

Stars at the end of each day 2,110 now
Jul 28, 2026 Nov 13, 2026
Net stars each day highest +1
+1 on Jul 28, 2026
Jul 28, 2026 Nov 13, 2026

The star count of each day is the latest count minus the net stars of the later days.

Add this Star History to a README

The images follow the light or dark theme of the page that shows them, and update every hour. Add ?theme=light or ?theme=dark to the chart address to keep one theme.

Star History chart

[![Star History of asappresearch/sru](https://awesomerepos.com/asappresearch/sru/stars.svg)](https://awesomerepos.com/asappresearch/sru)

Badge

[![AwesomeRepos](https://awesomerepos.com/asappresearch/sru/badge.svg)](https://awesomerepos.com/asappresearch/sru)

Timeline

It gained stars on 8 of the 109 days recorded since Jul 28, 2026.

Its largest 7 days were Sep 16, 2026 to Sep 22, 2026: 3 stars.

In the 30 days to Nov 13, 2026 it got 2 stars, 33% fewer than in the 30 days before.

It had 2,102 stars before Jul 28, 2026 and has 2,110 stars now: 2,890 fewer than 5,000.

  1. Created on the Repository Host
  2. Release v3.0.0.dev3
  3. Release v2.6.0.dev: Support GPU/CUDA inference in torchscript model
  4. Release 2.6.0.dev3: Support GPU/CUDA inference in torchscript model
  5. Release v2.6.0.dev2: Support GPU/CUDA inference in torchscript model; fix an issue
  6. Release v2.6.0: GPU inference in Torchscript model; post layer norm
  7. Latest push
  8. Largest star day recorded: +1 stars
  9. +1 stars in one day
  10. +1 stars in one day
  11. Entered the Repository Index: 2,110 stars on 2026-11-12

The timeline comes from the creation date and the releases on the Repository Host, the Admission, the Star History, and the Observations. Star milestones show only when the Star History records the day. The list shows up to 5 stable releases from the latest 10 releases recorded. When none of them is stable, one item counts the pre-releases. On the chart of net stars each day, a solid line marks each recorded release.

Forks and pushes

From 2 Observations, Nov 13, 2026 – Nov 14, 2026. Forks 0. AwesomeRepos saw a new push on 0 of 1 days.

Forks 305
  1. Nov 14, 2026: no new push

A filled day: the last push time changed since the Observation before it.

Health facts

Measured facts in four separate dimensions, each with a date and a source. AwesomeRepos does not add them into one score. AwesomeRepos reads the weekly commits, the changelog, and the community files each week for the 5,000 visible repositories with the most stars and for each rising repository. How AwesomeRepos defines each check

Copies a prompt for a coding agent. It has 1 task for the maintainers of asappresearch/sru.

Maintenance

1 of 4 checks (2 without data)
  • Yes: Not archived

    GitHub does not mark the repository as archived. Source

  • No: A push in the last 90 days

    Last push on 2022-01-04, 1774 days ago. Source

  • No data: Commits in the last 13 weeks

    No data: AwesomeRepos has not read the weekly commits.

  • No data: Commits in 26 or more of the last 52 weeks

    No data: AwesomeRepos has not read the weekly commits.

Releases

1 of 3 checks (1 without data)
  • No: A release in the last 365 days

    Newest release v2.7.0-rc1 on 2022-01-04, 1774 days ago. 0 releases in the last 365 days. Source

  • Yes: The newest release tag is a semantic version

    The newest release tag is v2.7.0-rc1. Source

  • No data: A changelog file at the root

    No data: AwesomeRepos has not scanned this repository.

Security practice

0 of 1 check (1 without data)
  • No data: A security policy

    No data: AwesomeRepos has not scanned this repository.

AwesomeRepos has not asked OpenSSF Scorecard about this repository.

Community files

1 of 3 checks (2 without data)
  • Yes: A licence

    GitHub finds the licence MIT. Source

  • No data: A contributing guide

    No data: AwesomeRepos has not scanned this repository.

  • No data: A code of conduct

    No data: AwesomeRepos has not scanned this repository.

Dependencies in the index

This section shows the packages that connect this repository to other repositories in the index.

The GitHub dependency graph of this repository names 10 direct packages (scanned on Nov 14, 2026). Packages from 7 other repositories in the index are among them.

No scanned repository names a package from this repository.

Uses Used by asappresearch/sru pytorch/pytorch pytorch/pytorch pandas-dev/pandas pandas-dev/pandas explosion/spaCy explosion/spaCy numpy/numpy numpy/numpy pytest-dev/pytest pytest-dev/pytest cupy/cupy cupy/cupy PyCQA/flake8 PyCQA/flake8 None in the scan
An arrow points from the repository that names a package to the repository that the package comes from.

Uses (in the index) · 7

Used by (in the index) · 0

None.

Sources: the GitHub dependency graph of each repository, and deps.dev for the source repository of each package (checked on Nov 4, 2026). A dependency graph also names development packages. deps.dev takes most source repositories from package metadata. How the dependency graph is made

Observations

Latest Observation, Nov 14, 2026: 2,110 stars, 305 forks, last push Jan 4, 2022, not archived. One of 2 Observations since Nov 13, 2026.

Report a problem with this page

Do not include personal data. AwesomeRepos keeps the message, the page, and the time.