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

ggml : check cuda and metal argsort limits and add test (#16323)

Browse Source 
* check cuda argsort limits and add test

* add metal check
This commit is contained in:
Sigbjørn Skjæret
2025-09-29 11:09:00 +02:00
committed by GitHub
parent 3a2bdcda0b
commit adc76347d7
3 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -6567,6 +6567,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {16, 10, 10, 10}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {60, 10, 10, 10}, order)); // qwen
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {1024, 1, 1, 1}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {16384, 1, 1, 1}, order)); // bailingmoe2 (group selection)
}
for (ggml_scale_mode mode : {GGML_SCALE_MODE_NEAREST, GGML_SCALE_MODE_BILINEAR}) {