Bellman281/esp32-tinyLLM

Rust inference engine for a 28.9M-parameter PLE TinyLM on the ESP32-S3 — 9.4 tok/s, faster than the C implementation it was ported from

语言：Rust · GitHub 星标：48 · Fork：3

话题：embedded · esp32 · esp32-s3 · inference-engine · llm · quantization · rust · rust-crate

在 GitHub 上查看原仓库