mamba-rs 0.7.3

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

mamba-rs

There is currently very little information to present on this page because Docs.rs has only limited support for extracting structured feature metadata from Cargo crates. This issue is tracked in Rust RFC #3416. Check this library's main docs, readme, and Cargo.toml in case its authors have documentation for features available there instead.

This version has 10 feature flags, 0 of them enabled by default.

default

This feature flag does not enable additional features.

accelerate

This feature flag does not enable additional features.

cli

cuda

cuda-cublaslt-qualification

cudarc

gemm

gemm-blas

hf

nccl

qualification

This feature flag does not enable additional features.