ClaudeBot/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: work around NV bug with argsort_large.comp (#28975)

Browse Source
This commit is contained in:
Jeff Bolz
2026-09-16 18:40:07 -05:00
committed by GitHub
parent fb27a525d2
commit 4bc272fd72
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/vulkan-shaders/argsort_large.comp
+8
View File
@@ -27,6 +27,8 @@ layout (push_constant) uniform parameter {
uint inner_end;
} p;
shared int s;
void argsort(bool needs_bounds_check, const uint row) {
// bitonic sort
int col = int(gl_GlobalInvocationID.x);
@@ -35,6 +37,12 @@ void argsort(bool needs_bounds_check, const uint row) {
const uint row_offset = row * p.ncols;
uint idx_offset = row * p.ncols_padded;
// workaround for NV driver/compiler bug - dummy use of shared memory
if (gl_LocalInvocationIndex == 0) {
s = 0;
col += s;
}
bool need_barrier = false;
// initialize indices