CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

arg : add --no-mmproj-offload (#13093)

Browse Source 
* arg : add --no-mmproj-offload

* Update common/arg.cpp
This commit is contained in:
Xuan-Son Nguyen
2025-04-24 14:04:14 +02:00
committed by GitHub
parent 80982e815e
commit 7c727fbe39
3 changed files with 12 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
common/arg.cpp
View File

@@ -2140,6 +2140,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.no_mmproj = true;
}
).set_examples(mmproj_examples));
add_opt(common_arg(
{"--no-mmproj-offload"},
"do not offload multimodal projector to GPU",
[](common_params & params) {
params.mmproj_use_gpu = false;
}
).set_examples(mmproj_examples));
add_opt(common_arg(
{"--image"}, "FILE",
"path to an image file. use with multimodal models. Specify multiple times for batching",

1
common/common.h
View File

@@ -342,6 +342,7 @@ struct common_params {
// multimodal models (see examples/llava)
struct common_params_model mmproj;
bool mmproj_use_gpu = true; // use GPU for multimodal model
bool no_mmproj = false; // explicitly disable multimodal model
std::vector<std::string> image; // path to image file(s)