tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-07 11:48:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: Split large mul_mat_id to fit in shared memory (#14451)

Browse Source
This commit is contained in:
Jeff Bolz
2025-07-01 03:43:08 -05:00
committed by GitHub
parent eff5e45443
commit 6a746cf9c4
2 changed files with 38 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/test-backend-ops.cpp
View File

@ -4623,6 +4623,11 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
// this case is verified (pass) in Intel(R) Data Center GPU Max 1100 (sycl backend) and NV A30 (cuda backend)
// test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F16, 512, 262144, 9216, {1, 1}, {1, 1}));
// 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));
}
for (ggml_type type_a : base_types) {
for (ggml_type type_b : {GGML_TYPE_F32 /*, GGML_TYPE_F16 */}) {
for (int n_mats : {4, 8}) {