sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 107 Packages Projects Releases Wiki Activity

model: Add PaddleOCR-VL model support (#18825)

Browse Source 
* support PaddleOCR-VL

* clip: update PaddleOCR model loader parameters to prevent OOM during warmup

* [update] add paddleocr vl text model instead of ernie4.5

* [update] restore change of minicpmv

* [update] format

* [update] format

* [update] positions and patch merge permute

* [update] mtmd_decode_use_mrope for paddleocr

* [update] image min/max pixels

* [update] remove set_limit_image_tokens

* upate: preprocess without padding

* clean up

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
megemini
2026-02-20 00:05:25 +08:00
committed by GitHub
parent abb9f3c42b
commit 237958db33
16 changed files with 327 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip.cpp
+48
View File
@@ -841,6 +841,10 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
{
builder = std::make_unique<clip_graph_kimivl>(ctx, img);
} break;
case PROJECTOR_TYPE_PADDLEOCR:
{
builder = std::make_unique<clip_graph_paddleocr>(ctx, img);
} break;
case PROJECTOR_TYPE_KIMIK25:
{
builder = std::make_unique<clip_graph_kimik25>(ctx, img);
@@ -1256,6 +1260,14 @@ struct clip_model_loader {
hparams.audio_window_len = 400;
hparams.audio_hop_len = 160;
} break;
case PROJECTOR_TYPE_PADDLEOCR:
{
hparams.n_merge = 2;
get_u32(KEY_IMAGE_MIN_PIXELS, hparams.image_min_pixels);
get_u32(KEY_IMAGE_MAX_PIXELS, hparams.image_max_pixels);
hparams.set_warmup_n_tokens(28*28); // avoid OOM on warmup
} break;
case PROJECTOR_TYPE_LFM2A:
{
// audio preprocessing params
@@ -1704,6 +1716,7 @@ struct clip_model_loader {
model.mm_2_b = get_tensor(string_format(TN_LLAVA_PROJ, 2, "bias"));
} break;
case PROJECTOR_TYPE_KIMIVL:
case PROJECTOR_TYPE_PADDLEOCR:
case PROJECTOR_TYPE_KIMIK25:
{
model.mm_input_norm_w = get_tensor(TN_MM_INP_NORM);
@@ -2990,6 +3003,7 @@ bool clip_image_preprocess(struct clip_ctx * ctx, const clip_image_u8 * img, str
case PROJECTOR_TYPE_QWEN25VL:
case PROJECTOR_TYPE_QWEN3VL:
case PROJECTOR_TYPE_GLM4V:
case PROJECTOR_TYPE_PADDLEOCR:
{
GGML_ASSERT(params.image_min_pixels > 0 && params.image_max_pixels > 0);
clip_image_u8 resized;
@@ -3330,6 +3344,7 @@ int clip_n_output_tokens_x(const struct clip_ctx * ctx, struct clip_image_f32 *
case PROJECTOR_TYPE_QWEN25VL:
case PROJECTOR_TYPE_QWEN3VL:
case PROJECTOR_TYPE_GLM4V:
case PROJECTOR_TYPE_PADDLEOCR:
case PROJECTOR_TYPE_YOUTUVL:
return (img->nx / params.patch_size) / 2;
default:
@@ -3346,6 +3361,7 @@ int clip_n_output_tokens_y(const struct clip_ctx * ctx, struct clip_image_f32 *
case PROJECTOR_TYPE_QWEN25VL:
case PROJECTOR_TYPE_QWEN3VL:
case PROJECTOR_TYPE_GLM4V:
case PROJECTOR_TYPE_PADDLEOCR:
case PROJECTOR_TYPE_YOUTUVL:
return (img->ny / params.patch_size) / 2;
default:
@@ -3443,6 +3459,13 @@ int clip_n_output_tokens(const struct clip_ctx * ctx, struct clip_image_f32 * im
int y_patch = CLIP_ALIGN(img->ny, out_patch_size) / out_patch_size;
n_patches = x_patch * y_patch;
} break;
case PROJECTOR_TYPE_PADDLEOCR:
{
// dynamic size
int n_merge = ctx->model.hparams.n_merge;
int stride = n_merge * n_merge;
n_patches = CLIP_ALIGN(n_patches, stride) / stride;
} break;
case PROJECTOR_TYPE_PIXTRAL:
case PROJECTOR_TYPE_LIGHTONOCR:
{
@@ -3690,6 +3713,30 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
}
}
set_input_i32("positions", positions);
} break;
case PROJECTOR_TYPE_PADDLEOCR:
{
const int merge_ratio = hparams.n_merge;
const int pw = image_size_width / patch_size;
const int ph = image_size_height / patch_size;
std::vector<int> positions(n_pos * 4);
int ptr = 0;
// NOTE: same as Qwen-VL, but x and y are swapped
for (int y = 0; y < ph; y += merge_ratio) {
for (int dy = 0; dy < 2; dy++) {
for (int x = 0; x < pw; x += merge_ratio) {
for (int dx = 0; dx < 2; dx++) {
positions[ ptr] = y + dy;
positions[ num_patches + ptr] = x + dx;
positions[2 * num_patches + ptr] = y + dy;
positions[3 * num_patches + ptr] = x + dx;
ptr++;
}
}
}
}
set_input_i32("positions", positions);
} break;
case PROJECTOR_TYPE_QWEN25VL:
@@ -4003,6 +4050,7 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx) {
return ctx->model.mm_2_w->ne[1];
case PROJECTOR_TYPE_LFM2:
case PROJECTOR_TYPE_KIMIVL:
case PROJECTOR_TYPE_PADDLEOCR:
case PROJECTOR_TYPE_KIMIK25:
return ctx->model.mm_2_w->ne[1];
case PROJECTOR_TYPE_COGVLM: