mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-06 09:46:50 +00:00
vulkan: fix group_norm (#10496)
Fix bad calculation of the end of the range. Add a backend test that covers the bad case (taken from stable diffusion). Fixes https://github.com/leejet/stable-diffusion.cpp/issues/439.
This commit is contained in:
@@ -19,7 +19,7 @@ void main() {
|
||||
|
||||
const uint tid = gl_LocalInvocationID.x;
|
||||
const uint start = gl_WorkGroupID.x * group_size + tid;
|
||||
const uint end = start + group_size;
|
||||
const uint end = (gl_WorkGroupID.x + 1) * group_size;
|
||||
|
||||
tmp[tid] = 0.0f;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user