Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-08 22:09:02 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into backend-sampling

Browse Source
This commit is contained in:
Daniel Bevenius
2025-11-26 17:52:29 +01:00
parent 90a3aff2c2 eec1e33a9e
commit 7c2bfb352e
20 changed files with 1475 additions and 391 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+15 -6
View File
@@ -7635,6 +7635,14 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {2, 8, 8192, 1}, order)); // bailingmoe2 (group selection)
}
for (int i = 0; i < 20; ++i) {
for (int k : {1, 2, 3, 7, 15, 100, 500, 1023, 9999}) {
if (k <= 1<<i) {
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {(1<<i), 1, 1, 1}, k));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {(1<<i) + 11, 1, 2, 1}, k));
}
}
}
for (int k : {1, 2, 3, 7, 15}) {
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {16, 10, 10, 10}, k));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {60, 10, 10, 10}, k));
@@ -8034,12 +8042,13 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {65000, 16, 1, 1}));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {200000, 1, 1, 1}));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {200000, 16, 1, 1}));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {65000, 16, 1, 1}, 40));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {65000, 1, 1, 1}, 40));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {65000, 1, 1, 1}, 1));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {200000, 1, 1, 1}, 400));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {200000, 1, 1, 1}, 40));
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {200000, 1, 1, 1}, 1));
for (auto k : {1, 10, 40, 400}) {
for (auto nrows : {1, 16}) {
for (auto cols : {k, 1000, 65000, 200000}) {
test_cases.emplace_back(new test_top_k(GGML_TYPE_F32, {cols, nrows, 1, 1}, k));
}
}
}
return test_cases;
}