An LLM inference engine written in pure Rust, designed to run large models on hardware that would normally refuse them.
-
Updated
Jun 1, 2026 - Rust
An LLM inference engine written in pure Rust, designed to run large models on hardware that would normally refuse them.
Local-first AI workspace with NP-DNA — a NeuroPlastic DNA Network for CPU-native training, memory, automation, and dashboard.
Research code for ProbeRoute, a probe-initialized sparse routing method for frozen-backbone multi-token prediction
Add a description, image, and links to the sparse-routing topic page so that developers can more easily learn about it.
To associate your repository with the sparse-routing topic, visit your repo's landing page and select "manage topics."