tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-30 06:03:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

vulkan/cuda: Fix im2col when KW!=KH (#14789)

Browse Source 
The tid is decomposed into "ow + ky*OW + kx*OW*KH". Change "ksize" to match.
This commit is contained in:
Jeff Bolz
2025-07-21 06:35:40 -05:00
committed by Aaron Teo
parent 8410b085ea
commit a2cdf559c2
3 changed files with 4 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/im2col.cu
View File

@@ -10,7 +10,7 @@ static __global__ void im2col_kernel(
return;
}
const int64_t ksize = OW * (KH > 1 ? KW : 1);
const int64_t ksize = OW * KH;
const int64_t kx = i / ksize;
const int64_t kd = kx * ksize;
const int64_t ky = (i - kd) / OW;

6
ggml/src/ggml-vulkan/vulkan-shaders/im2col.comp
View File

@@ -40,12 +40,10 @@ void main() {
const uint src_base = ic * p.offset_delta + batch * p.batch_offset;
const uint dst_base = ((batch * p.OH + oh) * p.OW) * p.CHW + ic * (p.KW * p.KH);
const int oh_s1 = int(oh) * p.s1;
const uint ksize = p.OW * (p.KH > 1 ? p.KW : 1);
const uint ksize = p.OW * p.KH;
const uint base_linear_idx = gidx * NUM_ITER;
const uint max_ky = ksize / p.OW;
uint current_kx = base_linear_idx / ksize;
const uint rem = base_linear_idx - (current_kx * ksize);
uint current_ky = rem / p.OW;
@@ -76,7 +74,7 @@ void main() {
if (++current_ix == p.OW) {
current_ix = 0;
if (++current_ky == max_ky) {
if (++current_ky == p.KH) {
current_ky = 0;
current_kx++;
}