nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

mtmd: refactor preprocessor, add mtmd_image_preproc_out (#24736)

Browse Source 
* add mtmd_image_preproc_out

* add dev docs

* remove unused clip API

* rm unused clip_image_f32_batch::grid

* change preprocess() call signature
This commit is contained in:
Xuan-Son Nguyen
2026-06-18 12:04:39 +02:00
committed by GitHub
parent 9724f664e8
commit 24bba7b98e
8 changed files with 279 additions and 370 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/multimodal.md
View File

@@ -1,10 +1,11 @@
# Multimodal
llama.cpp supports multimodal input via `libmtmd`. Currently, there are 2 tools support this feature:
- [llama-mtmd-cli](../tools/mtmd/README.md)
- [llama-cli](../tools/cli/README.md)
- [llama-server](../tools/server/README.md) via OpenAI-compatible `/chat/completions` API
- [llama-mtmd-cli](../tools/mtmd/README.md), for testing and development
Currently, we support **image** and **audio** input. Audio is highly experimental and may have reduced quality.
Currently, we support **image**, **audio** and **video** input.
To enable it, you can use one of the 2 methods below: