rten-generate

Crates.iorten-generate
lib.rsrten-generate
version0.22.1
created_at2024-07-05 21:09:36.400636+00
updated_at2025-09-18 18:22:28.925717+00
descriptionUtilities to simplify running auto-regressive models with RTen
homepagehttps://github.com/robertknight/rten
repositoryhttps://github.com/robertknight/rten
max_upload_size
id1293359
size98,389
Robert Knight (robertknight)

documentation

README

rten-generate is a layer on top of RTen which handles the generation loop for auto-regressive transformer models (aka. "transformer decoders" or "generative AI"). This includes managing the KV cache, sampling and post-processing logits etc.

Commit count: 3725

cargo fmt