/**
 * slice.ts — strided COLUMN slice of a row-major (rows, stride) tensor.
 *
 * Every block in this engine projects into one fused tensor and then splits it:
 * Mamba-1 into (x, z) and (Δ, B, C), Mamba-2/3 into (x, Δ) and (x, B, C),
 * attention into (Q, K, V). `LINEAR_FORWARD_WGSL` writes its output `(M, N)`
 * ROW-major, so each of those parts is a contiguous range of COLUMNS **within
 * every row** — not a contiguous range of the buffer.
 *
 * Splitting them with `copyBufferToBuffer` therefore took whole ROWS instead: it
 * is only the right answer when `M == 1` (batch × seq_len), and for any real
 * sequence it silently handed the block the wrong tensor. This kernel is the one
 * correct implementation; every block uses it.
 */
export declare const COL_SLICE_WGSL: string;
/** Entry point name of {@link COL_SLICE_WGSL}. */
export declare const COL_SLICE_ENTRY = "col_slice";
/**
 * `dst[r, 0..width) = src[r, offset..offset+width)` for every row.
 *
 * @param pipeline a pipeline built from {@link COL_SLICE_WGSL} / {@link COL_SLICE_ENTRY}
 * @param rows     batch * seqLen
 * @param stride   source row width (the fused projection's output features)
 */
export declare function dispatchColumnSlice(device: GPUDevice, pipeline: GPUComputePipeline, src: GPUBuffer, dst: GPUBuffer, rows: number, stride: number, offset: number, width: number): void;
//# sourceMappingURL=slice.d.ts.map