Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into xsn/fix_longest_edge_with_limit

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-07 15:38:55 +02:00
parent 7e1370694f c8e03ce812
commit b8b8738f92
8 changed files with 219 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip.cpp
+11 -3
View File
@@ -708,9 +708,10 @@ ggml_tensor * clip_graph::build_attn(
ggml_tensor * sinks) const {
// these nodes are added to the graph together so that they are not reordered
// by doing so, the number of splits in the graph is reduced
ggml_build_forward_expand(gf, q_cur);
ggml_build_forward_expand(gf, k_cur);
ggml_build_forward_expand(gf, v_cur);
// the order is fixed without the compute flag, so an unselected branch stays out of the compute set
ggml_build_forward_order(gf, q_cur);
ggml_build_forward_order(gf, k_cur);
ggml_build_forward_order(gf, v_cur);
ggml_tensor * q = ggml_permute(ctx0, q_cur, 0, 2, 1, 3);
//cb(q, "q", il);
@@ -1764,6 +1765,10 @@ struct clip_model_loader {
// qwen2 encoder is GQA, requires KEY_N_HEAD_KV
get_u32(string_format(KEY_N_HEAD_KV, "vision"), hparams.n_head_kv);
}
// unlimited-ocr shares the v1 projector but tiles up to 32
get_u32(KEY_PREPROC_MIN_TILES, hparams.preproc_min_tiles, false);
get_u32(KEY_PREPROC_MAX_TILES, hparams.preproc_max_tiles, false);
GGML_ASSERT(hparams.preproc_min_tiles <= hparams.preproc_max_tiles);
} break;
case PROJECTOR_TYPE_HUNYUANVL:
{
@@ -1912,6 +1917,9 @@ struct clip_model_loader {
if (hparams.image_max_pixels > 0) {
LOG_INF("%s: image_max_pixels: %d%s\n", __func__, hparams.image_max_pixels, hparams.custom_image_max_tokens > 0 ? " (custom value)" : "");
}
if (hparams.preproc_max_tiles > 0) {
LOG_INF("%s: preproc_tiles: %d - %d\n", __func__, hparams.preproc_min_tiles, hparams.preproc_max_tiles);
}
} else if (is_audio) {
LOG_INF("\n--- audio hparams ---\n");
LOG_INF("%s: n_mel_bins: %d\n", __func__, hparams.n_mel_bins);