CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix FA mask dim 2 and 3 (#14505)

Browse Source 
* ggml : fix FA mask dim 2 and 3

ggml-ci

* backends : unsupport batched FA in CUDA and Vulkan

ggml-ci

* vulkan : disable FA for mask->ne[2] != 1
This commit is contained in:
Georgi Gerganov
2025-07-03 10:46:57 +03:00
committed by GitHub
parent d4cdd9c1c3
commit 9067487c44
9 changed files with 26 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cpu/ops.cpp
View File

@@ -7799,7 +7799,7 @@ static void ggml_compute_forward_flash_attn_ext_f16(
memset(VKQ32, 0, DV*sizeof(float));
}
const ggml_fp16_t * mp = mask ? (ggml_fp16_t *)((char *) mask->data + iq1*mask->nb[1] + (iq3%mask->ne[2])*mask->nb[2]) : NULL;
const ggml_fp16_t * mp = mask ? (ggml_fp16_t *)((char *) mask->data + iq1*mask->nb[1] + (iq2%mask->ne[2])*mask->nb[2] + (iq3%mask->ne[3])*mask->nb[3]) : NULL;
// k indices
const int ik3 = iq3 / rk3;