Minimalist, high-performance ML framework for Rust with GPU support and LLM inference
Candle is a Rust-native ML framework by Hugging Face focused on performance and simplicity. It supports running state-of-the-art models like LLaMA, Whisper, and Stable Diffusion, with CUDA/Metal GPU acceleration and WASM browser demos.
Sign in to leave a comment.
No comments yet.
