e463bbdf65
* Move dequant_model to after the text_config merge Add new kimi-k2.5 keys to mtmd convert Update V_MMPROJ tensor mapping for new mm_projector.proj keys Update V_M_IMP_NORM for new mm_projector.pre_norm key * Fix a couple of oversights * Add image support for Kimi-K2.5 * Revert changes to KimiVLForConditionalGeneration * Fix an assert crash * Fix permute swapping w / h on accident * Kimi-K2.5: Use merged QKV for vision * Kimi-K2.5: pre-convert vision QK to use build_rope_2d * Kimi-K2.5: support non-interleaved rope for vision * Kimi-K2.5: fix min / max pixel * Kimi-K2.5: remove v/o permutes, unnecessary * Kimi-K2.5: update permute name to match * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Kimi-K2.5: replace build_rope_2d ggml_cont with ggml_view_3d pointers --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
118 lines
3.7 KiB
C
118 lines
3.7 KiB
C
#pragma once
|
|
|
|
#include "../clip-graph.h"
|
|
|
|
/*
|
|
* IMPORTANT: The mtmd module does NOT accept pull requests that are fully or predominantly AI-generated.
|
|
* We encourage human contributors to ensure the quality and reliability of the codebase.
|
|
*/
|
|
|
|
struct clip_graph_siglip : clip_graph {
|
|
clip_graph_siglip(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_pixtral : clip_graph {
|
|
clip_graph_pixtral(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_qwen2vl : clip_graph {
|
|
clip_graph_qwen2vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_qwen3vl : clip_graph {
|
|
clip_graph_qwen3vl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_youtuvl : clip_graph {
|
|
clip_graph_youtuvl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_minicpmv : clip_graph {
|
|
clip_graph_minicpmv(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_internvl : clip_graph {
|
|
clip_graph_internvl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_llama4 : clip_graph {
|
|
clip_graph_llama4(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_kimivl : clip_graph {
|
|
clip_graph_kimivl(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_cogvlm : clip_graph {
|
|
clip_graph_cogvlm(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_llava : clip_graph {
|
|
clip_graph_llava(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_whisper_enc : clip_graph {
|
|
clip_graph_whisper_enc(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_conformer : clip_graph {
|
|
clip_graph_conformer(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_glm4v : clip_graph {
|
|
clip_graph_glm4v(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
};
|
|
|
|
struct clip_graph_mobilenetv5 : clip_graph {
|
|
clip_graph_mobilenetv5(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
|
|
ggml_tensor * rms_norm_2d(
|
|
ggml_tensor * inp,
|
|
ggml_tensor * weight,
|
|
float eps = 1e-6f);
|
|
|
|
ggml_tensor* pad_same_2d(
|
|
ggml_tensor* inp,
|
|
int kernel_h,
|
|
int kernel_w,
|
|
int stride_h,
|
|
int stride_w,
|
|
int dilation_h = 1,
|
|
int dilation_w = 1);
|
|
|
|
ggml_tensor * build_edge_residual(
|
|
ggml_tensor * inp,
|
|
const mobilenetv5_block & block,
|
|
int stride);
|
|
|
|
ggml_tensor * build_inverted_residual(
|
|
ggml_tensor * inp,
|
|
const mobilenetv5_block & block,
|
|
int stride);
|
|
|
|
ggml_tensor * build_mobilenet_attn(
|
|
ggml_tensor * inp,
|
|
const mobilenetv5_block & block);
|
|
};
|
|
|
|
struct clip_graph_kimik25 : clip_graph {
|
|
clip_graph_kimik25(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
|
|
ggml_cgraph * build() override;
|
|
|
|
ggml_tensor * resize_position_embeddings_3d(uint32_t interpolation_mode);
|
|
};
|