CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : add TODO about KV padding requirement

Browse Source
This commit is contained in:
Georgi Gerganov
2025-09-28 17:25:37 +03:00
parent 66692977e8
commit 0629437601
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/src/ggml-cuda/fattn.cu
View File

@@ -208,6 +208,12 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
const int cc = ggml_cuda_info().devices[device].cc; const int cc = ggml_cuda_info().devices[device].cc;
// TODO: temporary until support is extended
// https://github.com/ggml-org/llama.cpp/pull/16148#issuecomment-3343525206
if (K->ne[1] % FATTN_KQ_STRIDE != 0) {
return BEST_FATTN_KERNEL_NONE;
}
switch (K->ne[0]) { switch (K->ne[0]) {
case 64: case 64:
case 128: case 128: