ggml : add note about mul_mat_id + disable mul_mat_id_dup tests (#30501)

This commit is contained in:
Georgi Gerganov authored and GitHub committed 2026-10-14 12:36:52 +03:00
1 parent df18bee11e
commit 8c2134a875
2 files changed
+8

No files matched your search

+3
View File
@@ -11028,6 +11028,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_TQ1_0, GGML_TYPE_F32, 28, 10, false, 1024, 1, 4096));
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_TQ1_0, GGML_TYPE_F32, 128, 8, false, 1024, 1, 2048));
// TODO: disabled until CUDA backend support is added [TAG_MUL_MAT_ID_DUPLICATE_ID]
#if 0
// repeated expert ids within a row
for (ggml_type ta : {GGML_TYPE_F16, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0}) {
for (int n : {9, 16, 33, 64}) {
@@ -11039,6 +11041,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_mul_mat_id_dup(ta, GGML_TYPE_F32, 1025, 10, false, 64, 33, 256, 1.0f, 0, true));
test_cases.emplace_back(new test_mul_mat_id_dup(ta, GGML_TYPE_F32, 2050, 10, true, 64, 33, 256));
}
#endif
for (ggml_type type_a : all_types) {
test_cases.emplace_back(new test_mul_mat_id(type_a, GGML_TYPE_F32, 4, 2, false, 64, 16, 3*ggml_blck_size(type_a)));