public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-17 11:45:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

ggml : remove GGML_KQ_MASK_PAD constant (llama/17910)

Browse Source 
* ggml : remove GGML_KQ_MASK_PAD constant

* cont : remove comment
This commit is contained in:
Georgi Gerganov
2025-12-12 17:53:24 +02:00
parent ca8ea18d06
commit cd9b8c6d18
2 changed files with 5 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml.c
-2
View File
@@ -5260,8 +5260,6 @@ struct ggml_tensor * ggml_flash_attn_ext(
if (mask) {
GGML_ASSERT(ggml_is_contiguous(mask));
GGML_ASSERT(mask->ne[1] >= GGML_PAD(q->ne[1], GGML_KQ_MASK_PAD) &&
"the Flash-Attention kernel requires the mask to be padded to GGML_KQ_MASK_PAD and at least n_queries big");
//GGML_ASSERT(ggml_can_repeat_rows(mask, qk));
GGML_ASSERT(q->ne[2] % mask->ne[2] == 0);