/**
 * mamba3_block.ts – Mamba-3 Mixer Block (Complex-valued MIMO SSM, inference-first).
 *
 * Three improvements over Mamba-2:
 *   1. Complex-valued states  — h ∈ ℂ^(N/2), stored as interleaved f32 pairs
 *   2. MIMO recurrence        — G×G block recurrence per head (default G=1 = SISO)
 *   3. ET discretisation      — B_bar = (A_bar − 1)·A⁻¹·B  (exact, not approx)
 *
 * Weight shapes vs Mamba-2 (same 9 tensors, different A_log shape):
 *   wInProj    : (D + 2*G*N_c*2 + H, dModel)   where N_c = dState (complex count)
 *   wConv      : (D + 2*G*N_c*2, K)
 *   bConv      : (D + 2*G*N_c*2,)
 *   A_log      : (H, 2)   ← [log|A|, arg(A)] per head
 *   dt_bias    : (H,)
 *   D_vec      : (H,)
 *   wOutProj   : (dModel, D)
 *   normWeight : (D,)
 *   preNormWeight: (dModel,)
 *
 * Implements SequenceLayer.
 */
import type { Mamba2BlockConfig } from './mamba2_block.js';
import type { SequenceLayer, LayerForwardResult, LayerParam } from './sequence_layer.js';
export interface Mamba3BlockConfig extends Mamba2BlockConfig {
    /** MIMO group size G. Default 1 = SISO (same as Mamba-2). */
    mimoGroup?: number;
}
export interface Mamba3Cache {
    stateCarry: GPUBuffer;
}
export declare class Mamba3Block implements SequenceLayer {
    readonly layerType: "mamba3";
    device: GPUDevice;
    config: Required<Mamba3BlockConfig>;
    dInner: number;
    dHead: number;
    /** Complex state count per head (N_c = dState in config). */
    nComplex: number;
    gpuWeights: Record<string, GPUBuffer>;
    pipelines: Record<string, GPUComputePipeline>;
    private _wslaMode;
    constructor(device: GPUDevice, config: Mamba3BlockConfig);
    private _initWeights;
    private _buildPipelines;
    forward(xBuf: GPUBuffer, batch: number, seqLen: number): LayerForwardResult;
    parameters(): LayerParam[];
    getTrainableParams(): LayerParam[];
    setWSLAMode(enabled: boolean): void;
    destroy(): void;
}
//# sourceMappingURL=mamba3_block.d.ts.map