1#pragma once
2
3void ggml_cuda_launch_mm_ids_helper(
4        const int32_t * ids, int32_t * ids_src1, int32_t * ids_dst, int32_t * expert_bounds,
5        int n_experts, int n_tokens, int n_expert_used, int nchannels_y, int si1, int sis1, cudaStream_t stream);