FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
#pragma once
void ggml_cuda_launch_mm_ids_helper(
const int32_t * ids, int32_t * ids_src1, int32_t * ids_dst, int32_t * expert_bounds,
int n_experts, int n_tokens, int n_expert_used, int nchannels_y, int si1, int sis1, bool write_inverse, cudaStream_t stream);
void ggml_cuda_launch_mm_ids_tile_map(
const int32_t * expert_bounds, int2 * tile_map, int n_experts, int J, int ntiles, int jt_none, cudaStream_t stream);