sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 107 Packages Projects Releases Wiki Activity

model, mtmd: fix gguf conversion for audio/vision mmproj (#21309)

Browse Source 
* fix gguf conversion for audio/vision mmproj

* fix test
This commit is contained in:
Xuan-Son Nguyen
2026-04-02 17:10:32 +02:00
committed by GitHub
parent 223373742b
commit 63f8fe0ef4
27 changed files with 1462 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/mtmd.cpp
+8
View File
@@ -394,6 +394,13 @@ struct mtmd_context {
img_end = "<|IMAGE_END|>";
image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
} break;
case PROJECTOR_TYPE_GEMMA4V:
{
// <|image> ... (image embeddings) ... <image|>
img_beg = "<|image>";
img_end = "<image|>";
image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
} break;
case PROJECTOR_TYPE_DEEPSEEKOCR:
{
img_end = "\n"; // prevent empty batch on llama-server
@@ -974,6 +981,7 @@ float * mtmd_get_output_embd(mtmd_context * ctx) {
bool mtmd_decode_use_non_causal(mtmd_context * ctx) {
switch (ctx->proj_type_v()) {
case PROJECTOR_TYPE_GEMMA3:
case PROJECTOR_TYPE_GEMMA4V:
return true;
default:
return false;