tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-16 07:38:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: add dynamic shared mem to softmax, refactor general usage (#14497)

Browse Source
This commit is contained in:
Aman Gupta
2025-07-03 07:45:11 +08:00
committed by GitHub
parent e75ba4c043
commit 55c2646b45
5 changed files with 57 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -4932,6 +4932,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_F32, {3072, 512, 2, 1}, {0, 2, 1, 3}));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {4096, 4096, 5, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {12888, 256, 5, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 4096, 5, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {1024, 1024, 10, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 1024, 10, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));