mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 25 Packages Projects Releases Wiki Activity

mtmd, server, common: expose modalities to /v1/models (#22952)

Browse Source 
* mtmd, server, common: expose modalities to /v1/models

* fix build

* rename to mtmd_caps
This commit is contained in:
Xuan-Son Nguyen
2026-05-12 19:08:07 +02:00
committed by GitHub
parent 927dada6c9
commit 7bfe120c21
10 changed files with 121 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip.cpp
+10 -2
View File
@@ -994,7 +994,7 @@ struct clip_model_loader {
bool has_audio = false;
// TODO @ngxson : we should not pass clip_ctx here, it should be clip_model
clip_model_loader(const char * fname) : fname(fname) {
clip_model_loader(const char * fname, bool skip_tensors = false) : fname(fname) {
struct ggml_context * meta = nullptr;
struct gguf_init_params params = {
@@ -1040,7 +1040,7 @@ struct clip_model_loader {
}
// tensors
{
if (!skip_tensors) {
for (int i = 0; i < n_tensors; ++i) {
const char * name = gguf_get_tensor_name(ctx_gguf.get(), i);
const size_t offset = gguf_get_tensor_offset(ctx_gguf.get(), i);
@@ -2927,6 +2927,14 @@ struct clip_init_result clip_init(const char * fname, struct clip_context_params
return {ctx_vision, ctx_audio};
}
struct clip_cap clip_get_cap(const char * fname) {
clip_cap res;
clip_model_loader loader(fname, /* skip_tensors= */ true);
res.has_vision = loader.has_vision;
res.has_audio = loader.has_audio;
return res;
}
struct clip_image_size * clip_image_size_init() {
struct clip_image_size * load_image_size = new struct clip_image_size();
load_image_size->width = 448;