CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: Remove splitting for mul_mat_id (#15568)

Browse Source 
row_ids only needs to hold the BN rows for the current tile.
This commit is contained in:
Jeff Bolz
2025-08-25 23:42:44 -05:00
committed by GitHub
parent 74f52f77f2
commit 34bdbbd7c2
4 changed files with 35 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/test-backend-ops.cpp
View File

@@ -6017,6 +6017,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
// test large experts*tokens
for (bool b : {false, true}) {
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 16, 16, b, 32, 1024, 16));
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 2, 2, b, 32, 8192, 64));
}
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 1, 1, false, 8, 16, 1));