CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues 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* vulkan: fix mmq out of bounds reads, streamline outdated matmul host code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

2
tests/test-backend-ops.cpp
View File

@@ -6987,6 +6987,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F32, GGML_TYPE_F32, 16, 32, 32, { 1, 1}, {1, 1}, {0, 1, 2, 3}, 64, 3));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F32, GGML_TYPE_F32, 64, 77, 77, {12,1}, {1,1}));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_Q4_0, GGML_TYPE_F32, 576, 512, 576, {1,1}, {1,1}));
#if 0
// test the mat-mat path for Metal
for (int k = 1; k < 512; ++k) {