Agent: Cursor, GitHub CopilotLLM: LLaMA, Whisper#rust#ml-framework#llm-inference#huggingface#gpu
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.