tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-27 02:28:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : Expose helper_decode_image_chunk (#13366)

Browse Source 
* mtmd: Expose helper_decode_image, output_embd_copy, image_tokens_copy/free

* Slim down

* Cleanups
This commit is contained in:
Matt Clayton
2025-05-08 14:25:39 -04:00
committed by GitHub
parent ee01d71e58
commit f05a6d71a0
2 changed files with 90 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/mtmd/mtmd.h
View File

@@ -231,6 +231,18 @@ MTMD_API int32_t mtmd_helper_eval_chunk_single(mtmd_context * ctx,
bool logits_last,
llama_pos * new_n_past);
// helper function to decode an image whose embeddings have already been calculated
// this helper will handle batching and pre/post decoding setup (for ex. gemma 3 requires non-causal attention)
// ret 0 on success, -1 on chunk not being a valid image chunk, 1 on decode failure
MTMD_API int32_t mtmd_helper_decode_image_chunk(mtmd_context * ctx,
struct llama_context * lctx,
const mtmd_input_chunk * chunk,
float * encoded_embd,
llama_pos n_past,
llama_seq_id seq_id,
int32_t n_batch,
llama_pos * new_n_past);
/////////////////////////////////////////
// test function, to be used in test-mtmd-c-api.c