Skip to main content

Module single_ssd

Module single_ssd 

Source
Expand description

§Single-SSD pathway (official-kernel form)

Realises the Mamba-3 trapezoidal recurrence as a single SSD call (the official Triton-SISO / Tilelang-MIMO form): a key scale scaleₜ = γₜ + (1−λₜ₊₁)·Δₜ₊₁, a strict lower-triangular intra-chunk mask, a same-step γ correction, and a boundary-β seed folded into the initial state.

Uses ≈ half the training memory of the double_ssd pathway. Its cache’s SSM accumulator h' has different mid-sequence semantics than the double-SSD state (hence a distinct cache type), but the two coincide at sequence boundaries and inter-convert via field-identity From impls.

Modules§

cache
The single-SSD cache (same fields as double-SSD, different ssm semantics).
prelude
Public re-exports for the single-SSD pathway.
single_ssd
forward_single_ssd (scale + boundary-β seed) and step_single_ssd.
ssd
The standard SSD kernels specialised to the single-pass scale/mask. Standard MIMO-first SSD kernels specialised to the single-pass form.