mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

mtmd: add clip_graph::build_mm() (#20751)

Browse Source 
* clip: add build_mm()

* apply to all models

* add TODO for bias overload
This commit is contained in:
Xuan-Son Nguyen
2026-03-19 13:11:39 +01:00
committed by GitHub
parent cd708db0cc
commit 1e64534570
15 changed files with 75 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/models/qwen2vl.cpp
+3 -3
View File
@@ -90,11 +90,11 @@ ggml_cgraph * clip_graph_qwen2vl::build() {
// self-attention
{
ggml_tensor * Qcur = ggml_add(ctx0,
ggml_mul_mat(ctx0, layer.q_w, cur), layer.q_b);
build_mm(layer.q_w, cur), layer.q_b);
ggml_tensor * Kcur = ggml_add(ctx0,
ggml_mul_mat(ctx0, layer.k_w, cur), layer.k_b);
build_mm(layer.k_w, cur), layer.k_b);
ggml_tensor * Vcur = ggml_add(ctx0,
ggml_mul_mat(ctx0, layer.v_w, cur), layer.v_b);
build_mm(layer.v_w, cur), layer.v_b);
Qcur = ggml_reshape_3d(ctx0, Qcur, d_head, n_head, n_patches);
Kcur = ggml_reshape_3d(ctx0, Kcur, d_head, n_head, n_patches);