mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-12-24 22:56:42 +00:00
2948c740a2
* sync : update scripts * sync : ggml * talk-llama : sync llama.cpp * make : WHISPER_CUBLAS -> WHISPER_CUDA * ci : try to fix sycl build * talk-llama : fix make build
33 lines
1.0 KiB
Plaintext
33 lines
1.0 KiB
Plaintext
#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);
|
|
CUDA_CHECK(cudaGetLastError());
|
|
}
|