CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
8 changed files with 79 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/mtmd/mtmd-cli.cpp
View File

@@ -132,11 +132,13 @@ struct mtmd_cli_context {
void init_vision_context(common_params & params) {
const char * clip_path = params.mmproj.path.c_str();
mtmd_context_params mparams = mtmd_context_params_default();
mparams.use_gpu = params.mmproj_use_gpu;
mparams.print_timings = true;
mparams.n_threads = params.cpuparams.n_threads;
mparams.verbosity = params.verbosity > 0 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_INFO;
mparams.flash_attn_type = params.flash_attn_type;
mparams.use_gpu = params.mmproj_use_gpu;
mparams.print_timings = true;
mparams.n_threads = params.cpuparams.n_threads;
mparams.verbosity = params.verbosity > 0 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_INFO;
mparams.flash_attn_type = params.flash_attn_type;
mparams.image_min_tokens = params.image_min_tokens;
mparams.image_max_tokens = params.image_max_tokens;
ctx_vision.reset(mtmd_init_from_file(clip_path, model, mparams));
if (!ctx_vision.get()) {
LOG_ERR("Failed to load vision model from %s\n", clip_path);