Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

vulkan: fix mmq out of bounds reads (#17108)

Browse Source 
* vulkan: fix mmq out of bounds reads, streamline outdated matmul host code

* fix mul_mat_id quantization call

* Fix compiler warnings
This commit is contained in:
Ruben Ortlam
2025-11-09 09:52:57 +01:00
committed by GitHub
parent 80a6cf6347
commit 8a3519b708
5 changed files with 113 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
+4 -2
View File
@@ -211,7 +211,9 @@ void main() {
const uint iqs = loadr_a;
[[unroll]] for (uint k_step = 0; k_step < BK_STEP; k_step++) {
block_a_to_shmem(k_step * BM + buf_ib, ib + k_step, iqs);
if (block + k_step * BK < end_k) {
block_a_to_shmem(k_step * BM + buf_ib, ib + k_step, iqs);
}
}
}
[[unroll]] for (uint l = 0; loadc_b + l < BN; l += loadstride_b) {
@@ -226,7 +228,7 @@ void main() {
const uint iqs = loadr_b;
[[unroll]] for (uint k_step = 0; k_step < BK_STEP; k_step++) {
block_b_to_shmem(k_step * BN + buf_ib, ib + k_step, iqs);
block_b_to_shmem(k_step * BN + buf_ib, ib + k_step, iqs, block + k_step * BK < end_k);
}
}