CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: Allow up to 4096 elements for mul_mat_id row_ids (#13326)

Browse Source 
This assert fired running Qwen_Qwen3-30B-A3B-Q2_K.gguf:

GGML_ASSERT(nei0 * nei1 <= 3072);

The tensor is 8 x 512. Increase this array size to accommodate.
This commit is contained in:
Jeff Bolz
2025-05-09 02:23:41 -05:00
committed by GitHub
parent d9c4accaff
commit 02115dcd9a
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_cm2.comp
View File

@@ -92,7 +92,7 @@ layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
#ifdef MUL_MAT_ID
layout (binding = 3) readonly buffer IDS {int data_ids[];};
shared u16vec4 row_ids[3072];
shared u16vec4 row_ids[4096];
layout(buffer_reference, std430, buffer_reference_align = 2) buffer decodeBufB {
B_TYPE b[];