Skip to content

Commit 4c33abe

Browse files
committed
add log
1 parent a5ca0eb commit 4c33abe

File tree

1 file changed

+2
-0
lines changed

1 file changed

+2
-0
lines changed

ggml/src/ggml-cuda/fattn.cu

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,7 @@
1010

1111
template <int D, int ncols2>
1212
static void ggml_cuda_flash_attn_ext_mma_f16_switch_ncols1(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
13+
GGML_LOG_INFO("ggml_cuda_flash_attn_ext_mma_f16_switch_ncols1: D=%d, ncols2=%d", D, ncols2);
1314
const ggml_tensor * Q = dst->src[0];
1415

1516
if (Q->ne[1] <= 8/ncols2) {
@@ -32,6 +33,7 @@ static void ggml_cuda_flash_attn_ext_mma_f16_switch_ncols1(ggml_backend_cuda_con
3233

3334
template <int ncols2>
3435
static void ggml_cuda_flash_attn_ext_mma_f16_switch_hs(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
36+
GGML_LOG_INFO("ggml_cuda_flash_attn_ext_mma_f16_switch_hs: ncols2=%d", ncols2);
3537
const ggml_tensor * Q = dst->src[0];
3638

3739
switch (Q->ne[0]) {

0 commit comments

Comments
 (0)