Rust-GPU/rust-cuda

Suggestion: WASI-NN CUDA

Open

#139 opened on Feb 2, 2025

View on GitHub
 (0 comments) (1 reaction) (0 assignees)Rust (240 forks)auto 404
enhancementhelp wanted

Repository metrics

Stars
 (5,261 stars)
PR merge metrics
 (PR metrics pending)

Description

A feature request; Implement the WASI-NN interface for CUDA so any WASM32-WASI [p1, p2 and future p3] runtime which wants a neural networking CUDA host can depend on a super efficient Rust implementation without needing to download a Docker image with gigabytes of other code.

Why? At the moment running AI code requires a Docker image with Python and CUDA which easily goes between 5GB o 15GB which for a serverless or edge use case is ridiculous.

Contributor guide