public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

cuda : fix "V is K view" check for non-unified KV cache (llama/19145)

This commit is contained in:
Georgi Gerganov 2026-01-28 09:15:27 +02:00
parent f28a733025
commit 7fb0f823de
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-common.cuh
View File

@ -789,7 +789,7 @@ void launch_fattn(
const ggml_tensor * K = dst->src[1];
const ggml_tensor * V = dst->src[2];
const bool V_is_K_view = V->view_src && V->view_offs == 0 && (V->view_src == K || V->view_src == K->view_src);
const bool V_is_K_view = V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs));
const ggml_tensor * mask = dst->src[3];
const ggml_tensor * sinks = dst->src[4];

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

@ -310,7 +310,7 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
}
}
const bool V_is_K_view = V->view_src && V->view_offs == 0 && (V->view_src == K || V->view_src == K->view_src);
const bool V_is_K_view = V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs));
const int cc = ggml_cuda_info().devices[device].cc;