vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-06-01 14:29:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

vulkan : fix FA mask load with bounds check (coopmat2) (#17606)

Browse source
This commit is contained in:
Acly 2025-11-30 01:03:21 +01:00 • committed by GitHub
parent ab49f094d2
commit 385c3da5e6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp
View file

@ -156,7 +156,7 @@ void main() {
tensorLayoutM = setTensorLayoutStrideNV(tensorLayoutM, m_stride, 1);
tensorLayoutM = setTensorLayoutClampValueNV(tensorLayoutM, 0xfc00); // -inf in float16_t
coopmat<float16_t, gl_ScopeWorkgroup, Br, Bc, gl_MatrixUseAccumulator> mv, mvmax;
coopmat<float16_t, gl_ScopeWorkgroup, Br, Bc, gl_MatrixUseAccumulator> mvmax;
coopMatLoadTensorNV(mv, data_m, m_offset, sliceTensorLayoutNV(tensorLayoutM, i * Br, Br, j * Bc, Bc));