CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

add ggml_pad_ext for cpu & cuda backend

Browse Source
This commit is contained in:
leejet
2025-07-26 00:28:52 +08:00
parent c92f9b4a68
commit 93c7e775b8
5 changed files with 113 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
ggml/src/ggml-cpu/ops.cpp
View File

@@ -8014,6 +8014,15 @@ static void ggml_compute_forward_pad_f32(
GGML_TENSOR_UNARY_OP_LOCALS
float * dst_ptr = (float *) dst->data;
const int32_t lp0 = ggml_get_op_params_i32(dst, 0);
const int32_t rp0 = ggml_get_op_params_i32(dst, 1);
const int32_t lp1 = ggml_get_op_params_i32(dst, 2);
const int32_t rp1 = ggml_get_op_params_i32(dst, 3);
const int32_t lp2 = ggml_get_op_params_i32(dst, 4);
const int32_t rp2 = ggml_get_op_params_i32(dst, 5);
const int32_t lp3 = ggml_get_op_params_i32(dst, 6);
const int32_t rp3 = ggml_get_op_params_i32(dst, 7);
// TODO: optimize
@@ -8022,10 +8031,12 @@ static void ggml_compute_forward_pad_f32(
for (int64_t i0 = 0; i0 < ne0; ++i0) {
for (int64_t i3 = 0; i3 < ne3; ++i3) {
const int64_t dst_idx = i3*(ne0*ne1*ne2) + i2*(ne0*ne1) + i1*ne0 + i0;
const float * src_ptr = (const float *)((char *) src0->data + i3*nb03 + i2*nb02 + i1*nb01 + i0*nb00);
if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
if ((i0 >= lp0 && i0 < ne0 - rp0) \
&& (i1 >= lp1 && i1 < ne1 - rp1) \
&& (i2 >= lp2 && i2 < ne2 - rp2) \
&& (i3 >= lp3 && i3 < ne3 - rp3)) {
const int64_t src_idx = (i3 - lp3)*nb03 + (i2 - lp2)*nb02 + (i1 - lp1)*nb01 + (i0 - lp0)*nb00;
const float * src_ptr = (const float *)((char *) src0->data + src_idx);
dst_ptr[dst_idx] = *src_ptr;
} else {
dst_ptr[dst_idx] = 0;