CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Implement overlap binary operators

Browse Source
This commit is contained in:
Reese Levine
2025-10-31 17:35:00 -07:00
parent da5296e1b5
commit ed710b36f5
4 changed files with 448 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -4840,7 +4840,7 @@ struct test_moe_expert_reduce : public test_case {
std::vector<ggml_tensor *> expert_views(n_expert_used);
for (int64_t i = 0; i < n_expert_used; ++i) {
expert_views[i] = ggml_view_2d(ctx, weighted, n_embd, n_tokens, weighted->nb[2], i * weighted->nb[1]);
expert_views[i] = ggml_view_2d(ctx, weighted, n_embd, n_tokens, weighted->nb[1], i * weighted->nb[1]);
std::string name = "expert_view_" + std::to_string(i);
ggml_set_name(expert_views[i], name.c_str());