| 1 | #include "common.cuh" |
| 2 | |
| 3 | void ggml_cuda_mul_mat_vec_f(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst, |
| 4 | const ggml_cuda_mm_fusion_args_host * fusion = nullptr); |
| 5 | |
| 6 | void ggml_cuda_op_mul_mat_vec_f( |
| 7 | ggml_backend_cuda_context & ctx, |
| 8 | const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i, |
| 9 | const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, const int64_t row_high, const int64_t src1_ncols, |
| 10 | const int64_t src1_padded_row_size, cudaStream_t stream); |
| 11 | |
| 12 | bool ggml_cuda_should_use_mmvf(enum ggml_type type, int cc, const int64_t * src0_ne, const size_t * src0_nb, int64_t ne11); |
| 13 | |