/**
 * GEMM (General Matrix Multiplication) operations
 */
import type { WebInferContext } from '../core/context.ts';
import type { Tensor } from '../core/tensor.ts';
/**
 * Batched matrix multiplication for fp16
 *
 * Computes C = A @ B for batched matrices
 *
 * @param ctx WebInfer context
 * @param a Input tensor A [B, M, K]
 * @param b Input tensor B [B, K, N]
 * @param output Optional output tensor C [B, M, N] for in-place operation
 * @returns Output tensor C [B, M, N]
 */
export declare function bmm_fp16(ctx: WebInferContext, a: Tensor, b: Tensor, output?: Tensor): Promise<Tensor>;
/**
 * Batched matrix multiplication for fp32
 *
 * @param ctx WebInfer context
 * @param a Input tensor A [B, M, K]
 * @param b Input tensor B [B, K, N]
 * @param output Optional output tensor C [B, M, N] for in-place operation
 * @returns Output tensor C [B, M, N]
 */
export declare function bmm_fp32(ctx: WebInferContext, a: Tensor, b: Tensor, output?: Tensor): Promise<Tensor>;