mamba-rs 0.7.1

Mamba SSM and Mamba-3 SISO in Rust with optional CUDA acceleration: inference and training (BPTT through the SSM state, AdamW) on CPU and GPU, custom NVRTC-compiled kernels, CUDA Graph capture, f32 / bf16 / f16 storage, deterministic batch-invariant GEMMs by default with explicit cuBLAS Fast and Pedantic modes.
Documentation 
1
2
3
4
5
6
7
8

//! Shared operations: dimensions, BLAS, math, normalization utilities.

pub mod blas;
pub mod dims;
pub mod fast_math;
pub mod norms;

pub use dims::{MambaDims, MambaRecurrentState};