mojolearn.Mamba1BlockInference

class mojolearn.Mamba1BlockInference(weights)

Bases: _RecurrentBlockInference, Mamba1Block

Forward-only Mamba1Block on the CPU, from weights trained on a GPU.

Takes the same constructor arguments as Mamba1Block (its ten named weights) and applies the same weight checks. Supports forward(x, lengths=None) from a zero state, allocate_state(B), forward(x, state) and step(x, state); decoding one token at a time with a carried state gives the same bits as one forward pass over the whole sequence. backward raises NotImplementedError. Runs on the host binding shipped with mojolearn; it is loaded on first use, so an install without it still imports and raises when the class is used.

__init__(weights)

Methods

allocate_state(batch_size)	Return a zero Mamba1State for batch_size sequences.
backward(x, grad_output)	Gradients of a zero-state prefill (a vector-Jacobian product).
decode_session(state)	Open a Mamba1DecodeSession for fast token-by-token decoding.
forward(x[, state, lengths])	Run the block over a sequence.
get_params([deep])
numeric_mode_used()	The numeric mode this estimator runs in.
set_params(**params)	Set constructor parameters.
step(x, state)	Run one decode token.
vendor_used()	The GPU backend this estimator runs on.