thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

cuda : fix argsort with 64k+ rows (#16849)

Browse source
This commit is contained in:
Sigbjørn Skjæret 2025-10-30 08:56:28 +01:00 • committed by GitHub
parent d7395115ba
commit 229bf68628
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tests/test-backend-ops.cpp
View file

@ -7111,7 +7111,8 @@ 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)
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {16384, 1, 1, 1}, order)); // many backends only handle up to 1024
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {2, 8, 8192, 1}, order)); // bailingmoe2 (group selection)
}
for (ggml_scale_mode mode : {GGML_SCALE_MODE_NEAREST, GGML_SCALE_MODE_BILINEAR}) {