mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-16 03:26:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: fix assertion when qy_needs_dequant (#12068)

Browse Source 
Looks like a copy/paste bug from qx_needs_dequant.
This commit is contained in:
Jeff Bolz 2025-02-25 09:30:21 -06:00 committed by GitHub
parent 401af80b54
commit a82c9e7c23
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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/ggml-vulkan.cpp
View File

@ -4192,7 +4192,7 @@ static void ggml_vk_mul_mat_q_f16(ggml_backend_vk_context * ctx, vk_context& sub
}
if (qy_needs_dequant) {
d_Y = ctx->prealloc_y;
GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03);
GGML_ASSERT(d_Y->size >= y_sz * ne12 * ne13);
} else {
d_Y = d_Qy;
y_buf_offset = qy_buf_offset;
@ -4769,7 +4769,7 @@ static void ggml_vk_mul_mat_id_q_f16(ggml_backend_vk_context * ctx, vk_context&
}
if (qy_needs_dequant) {
d_Y = ctx->prealloc_y;
GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03);
GGML_ASSERT(d_Y->size >= y_sz * ne12 * ne13);
} else {
d_Y = d_Qy;
y_buf_offset = qy_buf_offset;