extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-11-07 08:34:37 +01:00
Code Issues Packages Projects Releases Wiki Activity

sync : llama.cpp (skip)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-04-06 17:50:21 +03:00
parent 61b05815e0
commit 97878e53fd
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
3 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ggml-cuda/common.cuh
View File

@ -231,12 +231,6 @@ typedef float dfloat; // dequantize float
typedef float2 dfloat2;
#endif //GGML_CUDA_F16
// dmmv = dequantize_mul_mat_vec
// TODO: remove this?
#ifndef GGML_CUDA_DMMV_X
#define GGML_CUDA_DMMV_X 32
#endif
[[noreturn]]
static __device__ void no_device_code(
const char * file_name, const int line, const char * function_name, const int arch, const char * arch_list) {

4
ggml-cuda/dmmv.cu
View File

@ -2,10 +2,6 @@
#include "dequantize.cuh"
#include "convert.cuh"
#ifndef GGML_CUDA_MMV_Y
#define GGML_CUDA_MMV_Y 1
#endif
#ifndef K_QUANTS_PER_ITERATION
#define K_QUANTS_PER_ITERATION 2
#else

11
ggml-cuda/dmmv.cuh
View File

@ -1,5 +1,16 @@
#include "common.cuh"
// dmmv = dequantize_mul_mat_vec
// TODO: remove this?
#ifndef GGML_CUDA_DMMV_X
#define GGML_CUDA_DMMV_X 32
#endif
#ifndef GGML_CUDA_MMV_Y
#define GGML_CUDA_MMV_Y 1
#endif
void ggml_cuda_op_dequantize_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,