CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : support argsort for ne00 > 1024 (#17247)

Browse Source 
* metal : refactor argsort

* cont : sort chunks

* cont : merge sorted buckets

* cont : cleanup
This commit is contained in:
Georgi Gerganov
2025-11-14 09:36:06 +02:00
committed by GitHub
parent 2606b0adab
commit 45c6ef7307
8 changed files with 266 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/test-backend-ops.cpp
View File

@@ -7492,8 +7492,13 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {8, 1, 1, 1}, order));
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, {1023, 2, 1, 3}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {1024, 2, 1, 3}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {1025, 2, 1, 3}, order));
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, {2047, 2, 1, 3}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {2048, 2, 1, 3}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {2049, 2, 1, 3}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {2, 8, 8192, 1}, order)); // bailingmoe2 (group selection)
}