CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
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

5
ggml/src/ggml-opencl/ggml-opencl.cpp
View File

@@ -5587,7 +5587,9 @@ static void ggml_cl_scale(ggml_backend_t backend, const ggml_tensor * src0, cons
ggml_backend_opencl_context *backend_ctx = (ggml_backend_opencl_context *)backend->context;
float scale;
memcpy(&scale, dst->op_params, sizeof(scale));
float bias;
memcpy(&scale, ((int32_t *) dst->op_params) + 0, sizeof(float));
memcpy(&bias, ((int32_t *) dst->op_params) + 1, sizeof(float));
ggml_tensor_extra_cl * extra0 = (ggml_tensor_extra_cl *)src0->extra;
ggml_tensor_extra_cl * extrad = (ggml_tensor_extra_cl *)dst->extra;
@@ -5602,6 +5604,7 @@ static void ggml_cl_scale(ggml_backend_t backend, const ggml_tensor * src0, cons
CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), &extrad->data_device));
CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_ulong), &offsetd));
CL_CHECK(clSetKernelArg(kernel, 4, sizeof(float), &scale));
CL_CHECK(clSetKernelArg(kernel, 5, sizeof(float), &bias));
int n = ggml_nelements(dst)/4;

5
ggml/src/ggml-opencl/kernels/scale.cl
View File

@@ -8,9 +8,10 @@ kernel void kernel_scale(
ulong offset0,
global float4 * dst,
ulong offsetd,
float scale
float scale,
float bias
) {
src0 = (global float4*)((global char*)src0 + offset0);
dst = (global float4*)((global char*)dst + offsetd);
dst[get_global_id(0)] = src0[get_global_id(0)] * scale;
dst[get_global_id(0)] = src0[get_global_id(0)] * scale + bias;
}