We've first announced Candle, a minimalist ML framework in Rust 6 weeks ago. Since then, we've focused on adding various recent models and improved the framework so as to support the necessary features in an efficient way. You can checkout a gallery of the examples, supported models include:<p>- Large language models: LLaMA, LLaMA v2, Falcon, Phi-v1.5, StarCoder.
- Quantized models with the llama.cpp approach: LLaMA, T5, Phi-v1.5
- Image generation: Stable Diffusion (v1.5, v2.1, and XL), Wuerstchen.
- Computer Vision: DINOv2, yolo-v3, yolo-v8, Segment-Anything Model.
- Text-to-speech: Whisper.<p>Thanks to using pure Rust, it's easy to directly rpedict in the browser using WASM. See these examples using Yolo, Whisper, SAM, T5 and Llama 2 <a href="https://huggingface.co/collections/radames/candle-wasm-examples-650898dee13ff96230ce3e1f" rel="nofollow noreferrer">https://huggingface.co/collections/radames/candle-wasm-examp...</a>