CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

tests: add performance test for mul mat id (#15543)

Browse Source
This commit is contained in:
Eve
2025-08-26 15:42:49 +00:00
committed by GitHub
parent a6a58d6478
commit 44b1efa41a
1 changed files with 18 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/test-backend-ops.cpp
View File

@@ -6400,6 +6400,24 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
}
}
// qwen3-30b-a3b
for (int bs : {1, 4, 8, 512}) {
for (ggml_type type_a : {GGML_TYPE_F32, GGML_TYPE_F16, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0, GGML_TYPE_Q4_K, GGML_TYPE_Q6_K, GGML_TYPE_IQ2_XS}) {
for (ggml_type type_b : {GGML_TYPE_F32}) {
test_cases.emplace_back(new test_mul_mat_id(type_a, type_b, 128, 8, false, 768, bs, 2048, 1));
}
}
}
// gpt-oss-20b
for (int bs : {1, 4, 8, 512}) {
for (ggml_type type_a : {GGML_TYPE_MXFP4}) {
for (ggml_type type_b : {GGML_TYPE_F32}) {
test_cases.emplace_back(new test_mul_mat_id(type_a, type_b, 32, 4, false, 2880, bs, 2880, 1));
}
}
}
for (int K : {3, 5}) {
for (int IC : {256, 2560}) {
for (int IW_IH : {32, 64, 256}) {