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

mtmd : add video input support (#24269)

Browse Source 
* wip

* ok: lazy bitmap API

* remember to free lazy text

* wip

* add mtmd_helper_video

* support video input on server (base64 input)

* add MTMD_VIDEO config

* add timestamp

* update CLI

* cli: allow auto-completion for video

* add --video arg

* fix build

* update docs

* rename as suggested
This commit is contained in:
Xuan-Son Nguyen
2026-06-08 13:40:12 +02:00
committed by GitHub
parent c2b1518fd4
commit 8f83d6c271
16 changed files with 807 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/arg.cpp
View File

@@ -2221,8 +2221,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_OFFLOAD"));
add_opt(common_arg(
{"--image", "--audio"}, "FILE",
"path to an image or audio file. use with multimodal models, use comma-separated values for multiple files\n",
{"--image", "--audio", "--video"}, "FILE",
"path to an image, audio, or video file. use with multimodal models, use comma-separated values for multiple files\n",
[](common_params & params, const std::string & value) {
for (const auto & item : parse_csv_row(value)) {
params.image.emplace_back(item);