Skip to content

LLM inference in C/C++

C++ ggml

mtmd: fix Gemma 4 unified FPE (#24088)

Andrei94a220cd6745
diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
index 1abde5fb5f..2008198150 100644
--- a/tools/mtmd/clip.cpp
+++ b/tools/mtmd/clip.cpp
@@ -247,11 +247,11 @@ clip_graph::clip_graph(clip_ctx * ctx, const clip_image_f32 & img) :
n_embd(hparams.n_embd),
n_head(hparams.n_head),
n_head_kv(hparams.n_head_kv),
- d_head(n_embd / n_head),
+ d_head(n_head > 0 ? n_embd / n_head : 0),
n_layer(hparams.n_layer),
n_mmproj_embd(clip_n_mmproj_embd(ctx)),
eps(hparams.eps),
- kq_scale(1.0f / sqrtf((float)d_head)),
+ kq_scale(d_head > 0 ? 1.0f / sqrtf((float)d_head) : 0.0f),
flash_attn_type(ctx->flash_attn_type) {
struct ggml_init_params params = {
/*.mem_size =*/ ctx->buf_compute_meta.size(),