Files
llama.cpp/examples/llava/clip.h
Alex Brooks 7a2c913e66 llava : Add Granite Vision Support (#11794)
* Add super wip scripts for multimodal granite gguf

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Add example for converting mmgranite to gguf

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* remove hardcoded path

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Add vision feature layer to gguf params

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Clean up llava surgery and remove name substitution hacks

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Add transformers llava next tensor name mapping

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Make siglip / openclip mutuall exclusive

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix projector linear substitution

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix linear 2 substitution index

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Increase max flattened gridpoints to 64

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix hardcoded concat for multiple feature layers

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Pull vision feature layers out of gguf keys

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* fix num gridpoints and use all layers

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Avoid dropping last image encoder layer in llava models

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Use 10 for max number of patches

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Standardize vision feature layers

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Cleanup logs

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Update comment for vision feature layer init

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Update notes for alternative to legacy llm conversion script

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix notes rendering

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Add v prefix to vision feature layer log

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Use current defaults for feature layer

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Use constant for max gridpoints / feat layers, style fixes

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* clarify non-negative feature layers

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Remove CLIP_API from func signature

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* USE MAX_IMAGE_FEATURE_LAYERS const in layer calc

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Clarify feature layers are non negative ints and not uint

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix condition for reading feature layers

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* pop last llava layer when feature layers are unset

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix unset vision layer 0

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Update examples/llava/clip.cpp

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

* Reenable assertion for out of bounds get_rows

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Use std vector for gridpoints and feature layers

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Caculate max feature layer at load time

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Include base patch for granite vision allocation

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Fix trailing whitespace

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Add max num patches = 10 back for minicpmv

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Use unordered set to store feature layers

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Use max feature layer for postnorm

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

* Apply suggestions from code review

---------

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
2025-02-24 17:09:51 +01:00

109 lines
4.1 KiB
C

#ifndef CLIP_H
#define CLIP_H
#include <stddef.h>
#include <stdint.h>
#ifdef LLAMA_SHARED
# if defined(_WIN32) && !defined(__MINGW32__)
# ifdef LLAMA_BUILD
# define CLIP_API __declspec(dllexport)
# else
# define CLIP_API __declspec(dllimport)
# endif
# else
# define CLIP_API __attribute__ ((visibility ("default")))
# endif
#else
# define CLIP_API
#endif
#ifdef __cplusplus
extern "C" {
#endif
struct clip_ctx;
struct clip_image_size {
int width;
int height;
};
struct clip_image_u8_batch {
struct clip_image_u8 * data;
size_t size;
};
struct clip_image_f32_batch {
struct clip_image_f32 * data;
size_t size;
};
CLIP_API struct clip_ctx * clip_model_load (const char * fname, int verbosity);
CLIP_API struct clip_ctx * clip_model_load_cpu(const char * fname, int verbosity);
CLIP_API void clip_free(struct clip_ctx * ctx);
CLIP_API size_t clip_embd_nbytes(const struct clip_ctx * ctx);
CLIP_API size_t clip_embd_nbytes_by_img(const struct clip_ctx * ctx, int img_h, int img_w);
CLIP_API int32_t clip_image_size (const struct clip_ctx * ctx);
CLIP_API int32_t clip_patch_size (const struct clip_ctx * ctx);
CLIP_API int32_t clip_hidden_size(const struct clip_ctx * ctx);
// TODO: should be enum, not string
CLIP_API const char * clip_patch_merge_type(const struct clip_ctx * ctx);
CLIP_API const int32_t * clip_image_grid(const struct clip_ctx * ctx);
CLIP_API size_t get_clip_image_grid_size(const struct clip_ctx * ctx);
CLIP_API int clip_n_patches (const struct clip_ctx * ctx);
CLIP_API int clip_n_patches_by_img (const struct clip_ctx * ctx, struct clip_image_f32 * img);
CLIP_API int clip_n_mmproj_embd (const struct clip_ctx * ctx);
CLIP_API int clip_uhd_num_image_embeds_col(struct clip_ctx * ctx_clip);
CLIP_API void clip_add_load_image_size(struct clip_ctx * ctx_clip, struct clip_image_size * load_image_size);
CLIP_API struct clip_image_size * clip_get_load_image_size(struct clip_ctx * ctx_clip);
CLIP_API struct clip_image_size * clip_image_size_init();
CLIP_API struct clip_image_u8 * clip_image_u8_init ();
CLIP_API struct clip_image_f32 * clip_image_f32_init();
CLIP_API void clip_image_u8_free (struct clip_image_u8 * img);
CLIP_API void clip_image_f32_free(struct clip_image_f32 * img);
CLIP_API void clip_image_u8_batch_free (struct clip_image_u8_batch * batch);
CLIP_API void clip_image_f32_batch_free(struct clip_image_f32_batch * batch);
/** build image from pixels decoded by other libraries instead of stb_image.h for better performance. The memory layout is RGBRGBRGB..., input buffer length must be 3*nx*ny bytes */
CLIP_API void clip_build_img_from_pixels(const unsigned char * rgb_pixels, int nx, int ny, clip_image_u8 * img);
CLIP_API bool clip_image_load_from_file(const char * fname, struct clip_image_u8 * img);
/** interpret bytes as an image file with length bytes_length, and use the result to populate img */
CLIP_API bool clip_image_load_from_bytes(const unsigned char * bytes, size_t bytes_length, struct clip_image_u8 * img);
/** preprocess img and store the result in res_imgs, pad_to_square may be overridden to false depending on model configuration */
CLIP_API bool clip_image_preprocess(struct clip_ctx * ctx, const struct clip_image_u8 * img, struct clip_image_f32_batch * res_imgs );
CLIP_API struct ggml_tensor * clip_get_newline_tensor(const struct clip_ctx * ctx);
CLIP_API bool clip_image_encode (struct clip_ctx * ctx, int n_threads, struct clip_image_f32 * img, float * vec);
CLIP_API bool clip_image_batch_encode(struct clip_ctx * ctx, int n_threads, const struct clip_image_f32_batch * imgs, float * vec);
CLIP_API bool clip_model_quantize(const char * fname_inp, const char * fname_out, int itype);
CLIP_API int clip_is_minicpmv(const struct clip_ctx * ctx);
CLIP_API bool clip_is_glm(const struct clip_ctx * ctx);
CLIP_API bool clip_is_qwen2vl(const struct clip_ctx * ctx);
CLIP_API int get_deepest_feature_layer(const struct clip_ctx * ctx);
CLIP_API bool clip_encode_float_image (struct clip_ctx * ctx, int n_threads, float * img, int h, int w, float * vec);
#ifdef __cplusplus
}
#endif
#endif // CLIP_H