mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-31 22:53:52 -04:00
defe2158dd
* CUDA: mul_mat_v support for batch sizes > 1 * use 64 bit math for initial offset calculation
12 lines
656 B
Plaintext
12 lines
656 B
Plaintext
#include "common.cuh"
|
|
|
|
void ggml_cuda_mul_mat_vec(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_mul_mat_vec(
|
|
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);
|
|
|
|
bool ggml_cuda_should_use_mmv(enum ggml_type type, int cc, const int64_t * src0_ne, int64_t ne11);
|