llama.cpp/ggml/src/ggml-cuda/mmvq.cuh


1
2
3
4
5
6
7
8
9
10
11
12

#include "common.cuh"

#define MMVQ_MAX_BATCH_SIZE 8 // Max. batch size for which to use MMVQ kernels.

void ggml_cuda_mul_mat_vec_q(ggml_backend_cuda_context & ctx,
    const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst, const ggml_cuda_mm_fusion_args_host * fusion = nullptr);

void ggml_cuda_op_mul_mat_vec_q(
    ggml_backend_cuda_context & ctx,
    const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,
    const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, const int64_t row_high, const int64_t src1_ncols,
    const int64_t src1_padded_row_size, cudaStream_t stream);