9a3ea685b9
* CUDA: Fix bug in topk-moe for gpt-oss When using ggml_can_fuse_subgraph, the output nodes which are passed are wrong. This causes `test-backend-ops` to still fuse ndoes (because the nodes are not used elsewhere in the graph), but it actually doesn't fuse in the actual gpt-oss * fix for qwen3 too * change ifndef to ifdef |
||
|---|---|---|
| .. | ||
| cmake | ||
| include | ||
| src | ||
| .gitignore | ||
| CMakeLists.txt | ||