mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-14 14:59:52 +00:00
8 lines
400 B
Plaintext
8 lines
400 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
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);
|