thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

mtmd: add --image-min/max-tokens (#16921)

Browse source
This commit is contained in:
Xuan-Son Nguyen 2025-11-03 11:11:18 +01:00 • committed by GitHub
parent bf7b0c9725
commit 070ff4d535
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 79 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

14
common/arg.cpp
View file

@ -2768,6 +2768,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.image.emplace_back(value);
}
).set_examples({LLAMA_EXAMPLE_MTMD}));
add_opt(common_arg(
{"--image-min-tokens"}, "N",
"minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)",
[](common_params & params, int value) {
params.image_min_tokens = value;
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_IMAGE_MIN_TOKENS"));
add_opt(common_arg(
{"--image-max-tokens"}, "N",
"maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)",
[](common_params & params, int value) {
params.image_max_tokens = value;
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_IMAGE_MAX_TOKENS"));
if (llama_supports_rpc()) {
add_opt(common_arg(
{"--rpc"}, "SERVERS",