@tensorflow/tfjs-backend-webgpu

v4.22.0

This package adds a GPU accelerated [WebGPU](https://www.w3.org/TR/webgpu/) backend to TensorFlow.js. It currently supports the following models: - BlazeFace - BodyPix - Face landmarks detection - HandPose - MobileNet - PoseDetection - Universal sentence For more information about how to use this package see README

Latest version published 18 days ago

License: Apache-2.0

NPM

GitHub

Package Health Score

90 / 100

security
No known security issues
popularity
Recognized
maintenance
Healthy
community
Active

Explore Similar Packages

Security

No known security issues

All security vulnerabilities belong to production dependencies of direct and indirect packages.

Security and license risk for significant versions

All Versions

Version				Vulnerabilities	License Risk
4.22.0	\|	10/2024		0 C 0 H 0 M 0 L	0 H 0 M 0 L
4.21.0	\|	09/2024		0 C 0 H 0 M 0 L	0 H 0 M 0 L
4.20.0	\|	06/2024		0 C 0 H 0 M 0 L	0 H 0 M 0 L
4.19.0	\|	04/2024		0 C 0 H 0 M 0 L	0 H 0 M 0 L
4.12.0	\|	10/2023	Popular	0 C 0 H 0 M 0 L	0 H 0 M 0 L

License

Apache-2.0

Security Policy

Is your project affected by vulnerabilities?

Scan your projects for vulnerabilities. Fix quickly with automated fixes. Get started with Snyk for free.

Get started free

Popularity

Recognized

Weekly Downloads (2,207)

GitHub Stars: 18.46K
Forks: 1.92K
Contributors: 350

Direct Usage Popularity

The npm package @tensorflow/tfjs-backend-webgpu receives a total of 2,207 downloads a week. As such, we scored @tensorflow/tfjs-backend-webgpu popularity level to be Recognized.

Based on project statistics from the GitHub repository for the npm package @tensorflow/tfjs-backend-webgpu, we found that it has been starred 18,458 times.

Downloads are calculated as moving averages for a period of the last 12 months, excluding weekends and known missing data points.

Community

Active

Readme.md: Yes
Contributing.md: Yes
Code of Conduct: No
Contributors: 350
Funding: No

A good and healthy external contribution signal for @tensorflow/tfjs-backend-webgpu project, which invites more than one hundred open source maintainers to collaborate on the repository.

We found a way for you to contribute to the project! Looks like @tensorflow/tfjs-backend-webgpu is missing a Code of Conduct.

Embed Package Health Score Badge

Maintenance

Healthy

Commit Frequency

Open Issues: 300
Open PR: 233
Last Release: 18 days ago
Last Commit: 28 days ago

Further analysis of the maintenance status of @tensorflow/tfjs-backend-webgpu based on released npm versions cadence, the repository activity, and other data points determined that its maintenance is Healthy.

We found that @tensorflow/tfjs-backend-webgpu demonstrates a positive version release cadence with at least one new version released in the past 3 months.

As a healthy sign for on-going project maintenance, we found that the GitHub repository had at least 1 pull request or issue interacted with by the community.

Keep your project healthy

Check your package.json

Ensure all the packages you're using are healthy and well-maintained

Snyk Vulnerability Scanner

Get health score & security insights directly in your IDE

Package

Node.js Compatibility: not defined

Age: 5 years
Dependencies: 1 Direct
Versions: 49
Install Size: 17.6 MB
Dist-tags: 3
# of Files: 544
Maintainers: 10
TS Typings: Yes

@tensorflow/tfjs-backend-webgpu has more than a single and default latest tag published for the npm package. This means, there may be other tags available for this package, such as next to indicate future releases, or stable to indicate stable releases.

Readme

Usage

This package adds a GPU accelerated WebGPU backend to TensorFlow.js. It currently supports the following models:

BlazeFace
BodyPix
Face landmarks detection
HandPose
MobileNet
PoseDetection
Universal sentence encoder
AutoML Image classification
AutoML Object detection
Speech commands

Google Chrome started to support WebGPU by default in M113 on May 2, 2023.

Importing the backend

Via NPM

// Import @tensorflow/tfjs or @tensorflow/tfjs-core
import * as tf from '@tensorflow/tfjs';
// Add the WebGPU backend to the global backend registry.
import '@tensorflow/tfjs-backend-webgpu';
// Set the backend to WebGPU and wait for the module to be ready.
tf.setBackend('webgpu').then(() =&gt; main());

Via a script tag

FAQ

When should I use the WebGPU backend?

The mission of WebGPU backend is to achieve the best performance among all approaches. However, this target can not be met overnight, but we are committed to supporting it with rapid and continuous performance improvement. Many exciting features, like FP16, DP4A, will be brought in soon.

How many ops have you implemented?

See register_all_kernels.ts for an up-to-date list of supported ops. We love contributions. See the contributing document for more info.

Do you support training?

Maybe. There are still a decent number of ops that we are missing in WebGPU that are needed for gradient computation. At this point we are focused on making inference as fast as possible.

Do you work in node?

Yes. If you run into issues, please let us know.

How do I give feedback?

We'd love your feedback as we develop this backend! Please file an issue here.

Development

Building

yarn build

Testing

Currently the Canary channel of Chrome is used for testing of the WebGPU backend:

yarn test  # --test_env=CHROME_CANARY_BIN=/path/to/chrome

@tensorflow/tfjs-backend-webgpu dependencies

@tensorflow/tfjs-backend-cpu

@tensorflow/tfjs-backend-webgpu development dependencies

@babel/polyfill @tensorflow/tfjs-core jasmine jasmine-core karma karma-browserstack-launcher karma-chrome-launcher karma-commonjs karma-jasmine karma-typescript karma-jasmine-html-reporter karma-typescript-es6-transform

FAQs

What is @tensorflow/tfjs-backend-webgpu?

This package adds a GPU accelerated [WebGPU](https://www.w3.org/TR/webgpu/) backend to TensorFlow.js. It currently supp... Visit Snyk Advisor to see a full health score report for @tensorflow/tfjs-backend-webgpu, including popularity, security, maintenance & community analysis.

Is @tensorflow/tfjs-backend-webgpu popular?

The npm package @tensorflow/tfjs-backend-webgpu receives a total of 2,207 weekly downloads. As such, @tensorflow/tfjs-backend-webgpu popularity was classified as a recognized. Visit the popularity section on Snyk Advisor to see the full health analysis.

Is @tensorflow/tfjs-backend-webgpu well maintained?

We found that @tensorflow/tfjs-backend-webgpu demonstrated a healthy version release cadence and project activity. It has a community of 350 open source contributors collaborating on the project. See the full package health analysis to learn more about the package maintenance status.

Is @tensorflow/tfjs-backend-webgpu safe to use?

The npm package @tensorflow/tfjs-backend-webgpu was scanned for known vulnerabilities and missing license, and no issues were found. Thus the package was deemed as safe to use. See the full health analysis review.

Last updated on 5 November-2024, at 21:58 (UTC).

Build a secure application checklist

Select a recommended open source package

Minimize your risk by selecting secure & well maintained open source packages

DONE

Scan your app for vulnerabilities

Scan your application to find vulnerabilities in your: source code, open source dependencies, containers and configuration files

SCAN NOW

Fix identified vulnerabilities

Easily fix your code by leveraging automatically generated PRs

AUTO FIX

Monitor for new issues

New vulnerabilities are discovered every day. Get notified if your application is affected

MONITOR APP