mamba-rs 0.7.4

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
9
10
11
12

//! Mamba SSM (Selective State Space Model).
//!
//! Gu & Dao, "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" (2023).
//!
//! ## Structure
//! - `cpu/` — CPU inference + training (forward, backward)
//! - `gpu/` — GPU inference + training (CUDA kernels, CUDA Graphs)

pub mod cpu;

#[cfg(feature = "cuda")]
pub mod gpu;