Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-06 04:51:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : skip thumbnail for non-tiled LFM2 images (#27246)

Browse Source 
* mtmd : skip thumbnail for non-tiled LFM2 images

Matches HF behavior.

* Update tools/mtmd/mtmd-image.cpp

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Tarek Dakhran
2026-08-17 19:41:32 +02:00
committed by GitHub
parent 60eeeb6082
commit b75ecd1971
2 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/mtmd-image.cpp
+14
View File
@@ -999,6 +999,20 @@ mtmd_image_preprocessor_llava_uhd::slice_instructions mtmd_image_preprocessor_mi
// mtmd_image_preprocessor_lfm2
//
mtmd_image_preproc_out mtmd_image_preprocessor_lfm2::preprocess(const clip_image_u8 & img) {
auto const inst = get_slice_instructions(img.get_size());
if (!inst.slices.empty()) {
return mtmd_image_preprocessor_llava_uhd::preprocess(img);
}
// single tile: no thumbnail
// note: not using output.overview here because it will emit <|img_thumbnail|> token, which we don't want in this case
auto sliced = slice_image(img, inst);
mtmd_image_preproc_out output;
output.append(hparams, sliced.overview, true);
return output;
}
mtmd_image_preprocessor_llava_uhd::slice_instructions mtmd_image_preprocessor_lfm2::get_slice_instructions(const clip_image_size & original_size) {
mtmd_image_preprocessor_llava_uhd::slice_instructions inst;
const int align_size = hparams.patch_size * hparams.n_merge;
tools/mtmd/mtmd-image.h
+1
View File
@@ -145,6 +145,7 @@ struct mtmd_image_preprocessor_lfm2 : mtmd_image_preprocessor_llava_uhd {
static constexpr int tile_size = 512;
using mtmd_image_preprocessor_llava_uhd::mtmd_image_preprocessor_llava_uhd;
mtmd_image_preproc_out preprocess(const clip_image_u8 & img) override;
slice_instructions get_slice_instructions(const clip_image_size & original_size) override;
private: