extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-17 04:41:03 +02:00
Code Issues Packages Projects Releases Wiki Activity

whisper : reorganize source code + improve CMake (#2256)

Browse Source 
* scripts : update sync [no ci]

* files : reorganize [no ci]

* sync : llama.cpp

* cmake : link math library

* cmake : build normal ggml library

* files : move headers to include

* objc : fix path to ggml-metal.h

* ci : fix WHISPER_CUDA -> GGML_CUDA

* scripts : sync LICENSE [no ci]
This commit is contained in:
Georgi Gerganov
2024-06-26 19:34:09 +03:00
committed by GitHub
parent bf4cb4abad
commit e30c679928
361 changed files with 176536 additions and 20466 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
ggml/src/ggml-cuda/scale.cu Normal file
View File

@ -0,0 +1,31 @@
#include "scale.cuh"
static __global__ void scale_f32(const float * x, float * dst, const float scale, const int k) {
const int i = blockDim.x*blockIdx.x + threadIdx.x;
if (i >= k) {
return;
}
dst[i] = scale * x[i];
}
static void scale_f32_cuda(const float * x, float * dst, const float scale, const int k, cudaStream_t stream) {
const int num_blocks = (k + CUDA_SCALE_BLOCK_SIZE - 1) / CUDA_SCALE_BLOCK_SIZE;
scale_f32<<<num_blocks, CUDA_SCALE_BLOCK_SIZE, 0, stream>>>(x, dst, scale, k);
}
void ggml_cuda_op_scale(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const ggml_tensor * src0 = dst->src[0];
const float * src0_d = (const float *)src0->data;
float * dst_d = (float *)dst->data;
cudaStream_t stream = ctx.stream();
GGML_ASSERT(src0->type == GGML_TYPE_F32);
GGML_ASSERT( dst->type == GGML_TYPE_F32);
float scale;
memcpy(&scale, dst->op_params, sizeof(float));
scale_f32_cuda(src0_d, dst_d, scale, ggml_nelements(src0), stream);
}