mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

vulkan: Allow non-pow2 n_experts in topk_moe (#17872)

Browse Source
This commit is contained in:
Jeff Bolz
2025-12-13 01:40:04 -06:00
committed by GitHub
parent 2bc94e7928
commit 07a10c1090
3 changed files with 27 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+4
View File
@@ -7971,8 +7971,12 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (bool with_norm : {false, true}) {
test_cases.emplace_back(new test_topk_moe({8, 22, 1, 1}, 4, with_norm));
test_cases.emplace_back(new test_topk_moe({31, 22, 1, 1}, 8, with_norm));
test_cases.emplace_back(new test_topk_moe({32, 22, 1, 1}, 8, with_norm));
test_cases.emplace_back(new test_topk_moe({40, 22, 1, 1}, 8, with_norm));
test_cases.emplace_back(new test_topk_moe({71, 22, 1, 1}, 8, with_norm));
test_cases.emplace_back(new test_topk_moe({128, 1, 1, 1}, 128, with_norm));
test_cases.emplace_back(new test_topk_moe({129, 1, 1, 1}, 128, with_norm));
}
test_cases.emplace_back(new test_topk_moe({ 8, 22, 1, 1 }, 4, /*with_norm*/ false, /*delayed_softmax*/ true));