sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 114 Packages Projects Releases Wiki Activity

mtmd: refactor image preprocessing (#21031)

Browse Source 
* mtmd: refactor image pre-processing

* correct some places

* correct lfm2

* fix deepseek-ocr on server

* add comment to clarify about mtmd_image_preprocessor_dyn_size
This commit is contained in:
Xuan-Son Nguyen
2026-03-26 19:49:20 +01:00
committed by GitHub
parent ded446b34c
commit a73bbd5d92
8 changed files with 1602 additions and 1539 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip.h
-3
View File
@@ -97,9 +97,6 @@ struct clip_image_f32 * clip_image_f32_get_img(const struct clip_image_f32_batch
*/
void clip_build_img_from_pixels(const unsigned char * rgb_pixels, int nx, int ny, struct clip_image_u8 * img);
/** preprocess img and store the result in res_imgs, pad_to_square may be overridden to false depending on model configuration */
bool clip_image_preprocess(struct clip_ctx * ctx, const struct clip_image_u8 * img, struct clip_image_f32_batch * res_imgs );
struct ggml_tensor * clip_get_newline_tensor(const struct clip_ctx * ctx);
bool clip_image_encode (struct clip_ctx * ctx, int n_threads, struct clip_image_f32 * img, float * vec);