tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -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

28
ggml/src/ggml.c
View File

@@ -3069,12 +3069,14 @@ static struct ggml_tensor * ggml_scale_impl(
struct ggml_context * ctx,
struct ggml_tensor * a,
float s,
float b,
bool inplace) {
GGML_ASSERT(ggml_is_padded_1d(a));
struct ggml_tensor * result = inplace ? ggml_view_tensor(ctx, a) : ggml_dup_tensor(ctx, a);
ggml_set_op_params(result, &s, sizeof(s));
float params[2] = { s, b };
ggml_set_op_params(result, &params, sizeof(params));
result->op = GGML_OP_SCALE;
result->src[0] = a;
@@ -3086,14 +3088,30 @@ struct ggml_tensor * ggml_scale(
struct ggml_context * ctx,
struct ggml_tensor * a,
float s) {
return ggml_scale_impl(ctx, a, s, false);
return ggml_scale_impl(ctx, a, s, 0.0, false);
}
struct ggml_tensor * ggml_scale_inplace(
struct ggml_context * ctx,
struct ggml_tensor * a,
float s) {
return ggml_scale_impl(ctx, a, s, true);
return ggml_scale_impl(ctx, a, s, 0.0, true);
}
struct ggml_tensor * ggml_scale_bias(
struct ggml_context * ctx,
struct ggml_tensor * a,
float s,
float b) {
return ggml_scale_impl(ctx, a, s, b, false);
}
struct ggml_tensor * ggml_scale_bias_inplace(
struct ggml_context * ctx,
struct ggml_tensor * a,
float s,
float b) {
return ggml_scale_impl(ctx, a, s, b, true);
}
// ggml_set
@@ -5777,7 +5795,7 @@ static void ggml_compute_backward(
} break;
case GGML_OP_MEAN: {
if (src0_needs_grads) {
ggml_add1_or_set(ctx, cgraph, isrc0, ggml_scale_impl(ctx, grad, 1.0f/src0->ne[0], false));
ggml_add1_or_set(ctx, cgraph, isrc0, ggml_scale_impl(ctx, grad, 1.0f/src0->ne[0], 0.0, false));
}
} break;
case GGML_OP_REPEAT: {
@@ -5854,7 +5872,7 @@ static void ggml_compute_backward(
if (src0_needs_grads) {
float s;
memcpy(&s, tensor->op_params, sizeof(float));
ggml_add_or_set(ctx, cgraph, isrc0, ggml_scale_impl(ctx, grad, s, false));
ggml_add_or_set(ctx, cgraph, isrc0, ggml_scale_impl(ctx, grad, s, 0.0, false));
}
} break;
case GGML_OP_SET: {