wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix merge problem

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-06-06 00:19:40 +02:00
parent acca080f51
commit 5b0cfdfac1
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip.cpp
+3 -3
View File
@@ -3436,7 +3436,7 @@ int clip_n_output_tokens(const struct clip_ctx * ctx, struct clip_image_f32 * im
} break;
case PROJECTOR_TYPE_GEMMA4UA:
{
n_patches = img->nx; // no downsampling: one token per raw waveform frame
n_patches = img->nx(); // no downsampling: one token per raw waveform frame
} break;
case PROJECTOR_TYPE_GRANITE_SPEECH:
{
@@ -3451,7 +3451,7 @@ int clip_n_output_tokens(const struct clip_ctx * ctx, struct clip_image_f32 * im
// For 384×384 input: n = 24/8 = 3, query_side = 4 → 144.
const int window_side = ctx->model.hparams.downsample_window_side;
const int query_side = ctx->model.hparams.downsample_query_side;
const int side = img->nx / params.patch_size;
const int side = img->nx() / params.patch_size;
const int n = side / window_side;
n_patches = (query_side * n) * (query_side * n);
if (img->add_newline) {
@@ -4303,7 +4303,7 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
// reshapes as ggml_get_rows gathers. The names are set
// by g4v_gather() in models/granite4-vision.cpp.
const int patch_size = model.hparams.patch_size;
const int image_side = imgs.entries.front()->nx / patch_size;
const int image_side = imgs.entries.front()->nx() / patch_size;
const int window_side = hparams.downsample_window_side;
const int query_side = hparams.downsample_query_side;
const int n = image_side / window_side;
tools/mtmd/models/exaone4_5.cpp
+2 -2
View File
@@ -22,8 +22,8 @@ ggml_cgraph * clip_graph_exaone4_5::build() {
ggml_tensor * inp_raw = build_inp_raw();
ggml_tensor * inp = ggml_conv_2d(ctx0, model.patch_embeddings_0, inp_raw, patch_size, patch_size, 0, 0, 1, 1);
GGML_ASSERT(img.nx % (patch_size * 2) == 0);
GGML_ASSERT(img.ny % (patch_size * 2) == 0);
GGML_ASSERT(img.nx() % (patch_size * 2) == 0);
GGML_ASSERT(img.ny() % (patch_size * 2) == 0);
{
ggml_tensor * inp_1 = ggml_conv_2d(ctx0, model.patch_embeddings_1, inp_raw, patch_size, patch_size, 0, 0, 1, 1);