LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity

Fix fused grouped topk (#851)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-10-21 10:10:38 +03:00
committed by GitHub
co-authored by Iwan Kawrakow
parent c23a17b6fe
commit a27d661aeb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda.cu
+1 -1
View File
@@ -3187,7 +3187,7 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
cgraph->nodes[i+2]->op == GGML_OP_ADD &&
cgraph->nodes[i+3]->op == GGML_OP_GROUPED_TOPK &&
cgraph->nodes[i+4]->op == GGML_OP_GET_ROWS) {
cuda_bailingmoev2_experts(ctx, cgraph->nodes[i+4], cgraph->nodes[i+4]);
cuda_bailingmoev2_experts(ctx, cgraph->nodes[i+4], cgraph->nodes[i+3]);
i += 4;
} else {
ggml_cuda_op_sigmoid(ctx, dst);