ruvllm_sparse_attention 0.1.1

Subquadratic O(N log N) sparse attention kernel for Rust LLM inference on edge devices, with optional FastGRNN salience gating for near-linear O(N) scaling
Documentation

ruvllm_sparse_attention

There is very little structured metadata to build this page from currently. You should check the main library docs, readme, or Cargo.toml in case the author documented the features in them.

This version has 3 feature flags, 1 of them enabled by default.

default

std (default)

This feature flag does not enable additional features.

fp16

parallel