GitHub - huggingface/candle: Minimalist ML framework for Rust
github.com
Minimalist ML framework for Rust. Contribute to huggingface/candle development by creating an account on GitHub.

Out of the box models: Llama, Whisper, Falcon, StarCoder, etc, WASM support (run in browser), model training, and much much more, woo-hoo!

  • egeres@lemmy.ml
    ·
    1 year ago

    I can't believe I'll get excited about phone specs again 🙌🏻✨. Do you think it could be possible to parallelize computation among various phones to run inference on transformer models? I assume is not worth it since you would need to transfer a ton of data among devices to run attention per layer, but the llama people have pulled so many tricks at this point...