ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

CUDA: add mean operation (#14313)

Browse source 
* CUDA: add mean operation

* add back sum_rows_f32_cuda

* Review: early exit if col!=0
This commit is contained in:
Aman Gupta 2025-06-22 12:39:54 +08:00 • committed by GitHub
parent aa0ef5c578
commit aa064b2eb7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 54 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/test-backend-ops.cpp
View file

@ -4652,6 +4652,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
test_cases.emplace_back(new test_conv_transpose_2d({256, 256, 256, 1}, {3, 3, 16, 256}, 1));
test_cases.emplace_back(new test_mean(GGML_TYPE_F32, {256, 256, 3, 1}));
return test_cases;
}