tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-05 00:25:26 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add ggml_scale_bias (#14417)

Browse Source 
* ggml : add ggml_scale_bias

* ggml_vec_mad1_f32

* add more simd

* add CUDA

* sycl

* vulkan

* cann (placeholder)

* opencl

* will this fix cpu?

* fix cuda

* suggestions from coderabbit

* fix cann compile error

* vDSP_vsmsa

* rm __ARM_FEATURE_SVE

* use memcpy for op params

* make code looks more consistent

* use scalar for __ARM_FEATURE_SVE

* add x param to ggml_vec_mad1_f32
This commit is contained in:
Xuan-Son Nguyen
2025-07-09 18:16:12 +02:00
committed by GitHub
parent 26a48ad699
commit 98bab638fb
14 changed files with 139 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
ggml/src/ggml-cuda/scale.cu
View File

@@ -1,18 +1,18 @@
#include "scale.cuh"
static __global__ void scale_f32(const float * x, float * dst, const float scale, const int k) {
static __global__ void scale_f32(const float * x, float * dst, const float scale, const float bias, const int k) {
const int i = blockDim.x*blockIdx.x + threadIdx.x;
if (i >= k) {
return;
}
dst[i] = scale * x[i];
dst[i] = scale * x[i] + bias;
}
static void scale_f32_cuda(const float * x, float * dst, const float scale, const int k, cudaStream_t stream) {
static void scale_f32_cuda(const float * x, float * dst, const float scale, const float bias, 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);
scale_f32<<<num_blocks, CUDA_SCALE_BLOCK_SIZE, 0, stream>>>(x, dst, scale, bias, k);
}
void ggml_cuda_op_scale(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
@@ -25,7 +25,9 @@ void ggml_cuda_op_scale(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
GGML_ASSERT( dst->type == GGML_TYPE_F32);
float scale;
memcpy(&scale, dst->op_params, sizeof(float));
float bias;
memcpy(&scale, (float *) dst->op_params + 0, sizeof(float));
memcpy(&bias, (float *) dst->op_params + 1, sizeof(float));
scale_f32_cuda(src0_d, dst_d, scale, ggml_nelements(src0), stream);
scale_f32_cuda(src0_d, dst_d, scale, bias, ggml_nelements(src0), stream);
}