ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

mtmd : refactor llava-uhd preprocessing logic (#14247)

Browse source 
* mtmd : refactor llava-uhd preprocessing logic

* fix editorconfig
This commit is contained in:
Xuan-Son Nguyen 2025-06-18 10:43:57 +02:00 • committed by GitHub
parent 95402553a5
commit 413977de32
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 110 additions and 80 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tools/mtmd/clip.h
View file

@ -46,9 +46,6 @@ int32_t clip_get_hidden_size(const struct clip_ctx * ctx);
// TODO: should be enum, not string
const char * clip_patch_merge_type(const struct clip_ctx * ctx);
const int32_t * clip_image_grid(const struct clip_ctx * ctx);
size_t get_clip_image_grid_size(const struct clip_ctx * ctx);
int clip_n_output_tokens(const struct clip_ctx * ctx, struct clip_image_f32 * img);
// for M-RoPE, this will be the number of token positions in X and Y directions