git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp synced 2026-04-16 20:05:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: Fix FA coopmat1 invalid array indexing (llama/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 Georgi Gerganov
parent fd11cd97ab
commit 90bdcf2ef6
1 changed files with 2 additions and 2 deletions
Show Stats 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;