upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: only support F32/F16 for GGML_OP_REPEAT (#24533)

Browse Source
This commit is contained in:
leonardHONG
2026-06-15 14:11:00 +08:00
committed by GitHub
parent 6e9007ae61
commit 3686e9d643
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -8086,6 +8086,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_repeat(GGML_TYPE_F32, {10, 5, 4, ne3}, {1, 1, 1, 2}));
test_cases.emplace_back(new test_repeat(GGML_TYPE_I32, {10, 5, 4, ne3}, {2, 1, 1, 1}));
test_cases.emplace_back(new test_repeat(GGML_TYPE_I16, {10, 5, 4, ne3}, {1, 1, 1, 2}));
test_cases.emplace_back(new test_repeat(GGML_TYPE_BF16, {10, 5, 4, ne3}, {2, 1, 1, 1}));
}
for (bool view : {false, true}) {