Yakine Tahtah a00e47e422
mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech) (#22101)
* mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech)

Conformer encoder with Shaw relative position encoding,
QFormer projector, log-mel spectrogram with frame stacking.

Encoder uses GLU gating, folded batch norm, and SSM depthwise
conv. QFormer compresses encoder output via windowed
cross-attention (window=15, queries=3) into the LLM embedding
space.

Audio preprocessing: reflect-padded STFT, 80-bin mel filterbank,
dynamic range compression, 2x frame stacking (80->160 mel).

GGUF converter handles batch norm folding at export time,
fused K/V split, and Conv1d weight reshaping.

Tested against HF transformers reference: token-for-token match
on 30s/60s audio clips with greedy decoding.

* mtmd: rename gs_ prefixed tensors to generic/architecture names

* mtmd: use tensor_mapping.py for all granite_speech tensors

* convert: fold GraniteSpeechTextModel into GraniteModel

* mtmd: replace n_layer hack with explicit has_standard_layers flag

* mtmd: replace hardcoded magic numbers with GGUF hparams for granite speech

* mtmd: align KEY_A_ define spacing

* convert: register GraniteModel for GraniteSpeechForConditionalGeneration

* convert: fix ty type-check for GraniteSpeechMmprojModel registration

* mtmd: align TN_ define spacing

* mtmd: use generic layer loop for granite speech tensor loading

* mtmd: merge qformer_proj_layer into clip_layer

* mtmd: granite_speech remove redundant ggml_build_forward_expand on inputs

* mtmd: granite_speech add comment explaining why build_attn is not used

* mtmd: granite_speech hard-code eps in cpp, remove from GGUF metadata

* gguf: add spacing between granite_speech tensor mapping blocks

* mtmd: make generic audio layer_norm_eps read optional

* mtmd: granite_speech keep encoder eps in GGUF, only hard-code projector eps

* mtmd: align defines and struct fields in clip-impl.h and clip-model.h

* mtmd: fix alignment and ordering issues across granite speech files

* convert: granite_speech use filter_tensors instead of modify_tensors for skipping
2026-05-06 14:40:59 +02:00

179 lines
6.0 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_gemma4v : clip_graph {
clip_graph_gemma4v(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
ggml_tensor * build_mm(ggml_tensor * w, ggml_tensor * x) const 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_step3vl : clip_graph {
clip_graph_step3vl(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_yasa2 : clip_graph {
clip_graph_yasa2(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
ggml_tensor * layer_norm_channels(ggml_tensor * inp, ggml_tensor * w, ggml_tensor * b, float eps = 1e-6f);
ggml_tensor * convnext_grn(ggml_tensor * inp, ggml_tensor * w, ggml_tensor * b);
};
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_nemotron_v2_vl : clip_graph {
clip_graph_nemotron_v2_vl(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_paddleocr : clip_graph {
clip_graph_paddleocr(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
};
struct clip_graph_dotsocr : clip_graph {
clip_graph_dotsocr(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_deepseekocr : clip_graph {
clip_graph_deepseekocr(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_granite_speech : clip_graph {
clip_graph_granite_speech(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
};
struct clip_graph_gemma4a : clip_graph {
clip_graph_gemma4a(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
ggml_tensor * build_mm(ggml_tensor * w, ggml_tensor * x) const 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_hunyuanocr : clip_graph {
clip_graph_hunyuanocr(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_qwen3a : clip_graph {
clip_graph_qwen3a(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
ggml_cgraph * build() override;
};
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);
};