epwalsh/rust-dl-webserver

🦀 Example of serving deep learning models in Rust with batched prediction

27
/ 100
Experimental

This is an example for software engineers who need to deploy deep learning models that generate text, such as a GPT-2 model. It takes in text prompts and outputs generated text, efficiently handling multiple requests by processing them in batches, especially when a GPU is available. It's designed for developers building backend services for AI-powered applications.

No commits in the last 6 months.

Use this if you are a software engineer looking for a robust way to serve text generation models with good performance and stability.

Not ideal if you are a data scientist or end-user looking for a pre-built application to use directly without writing code.

AI-model-deployment backend-development text-generation-APIs GPU-acceleration web-services
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

34

Forks

5

Language

Rust

License

Last pushed

Mar 09, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/epwalsh/rust-dl-webserver"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.