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

vulkan: Fix FA coopmat1 invalid array indexing (#16365)

Browse Source 
When computing sinks, the cm1 shader was looping r from 0 to Br rather than
to rows_per_thread. I must have copied this from the scalar path (where it is
correct), and somehow it wasn't causing failures on current drivers.
This commit is contained in:
Jeff Bolz
2025-10-03 04:52:46 -05:00
committed by GitHub
parent ad126479c2
commit 0e1f838556
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp
View File

@@ -358,8 +358,8 @@ void main() {
}
if ((p.mask_n_head_log2 & SINK_ENABLE_BIT) != 0) {
[[unroll]] for (uint32_t r = 0; r < Br; ++r) {
float sink = perElemOpGetSink(r, 0u, ACC_TYPE(0), iq2);
[[unroll]] for (uint32_t r = 0; r < rows_per_thread; ++r) {
float sink = perElemOpGetSink(tile_row(r), 0u, ACC_TYPE(0), iq2);
float ms = 1.0f;
float vs = 1.0f;