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

gguf-py/gguf/gguf_writer.py

@@ -1260,6 +1260,24 @@ class GGUFWriter:
     def add_audio_stack_factor(self, value: int) -> None:
         self.add_uint32(Keys.ClipAudio.Projector.STACK_FACTOR, value)
 
+    def add_audio_chunk_size(self, value: int) -> None:
+        self.add_uint32(Keys.ClipAudio.CHUNK_SIZE, value)
+
+    def add_audio_conv_kernel_size(self, value: int) -> None:
+        self.add_uint32(Keys.ClipAudio.CONV_KERNEL_SIZE, value)
+
+    def add_audio_max_pos_emb(self, value: int) -> None:
+        self.add_uint32(Keys.ClipAudio.MAX_POS_EMB, value)
+
+    def add_audio_projector_window_size(self, value: int) -> None:
+        self.add_uint32(Keys.ClipAudio.Projector.WINDOW_SIZE, value)
+
+    def add_audio_projector_downsample_rate(self, value: int) -> None:
+        self.add_uint32(Keys.ClipAudio.Projector.DOWNSAMPLE_RATE, value)
+
+    def add_audio_projector_head_count(self, value: int) -> None:
+        self.add_uint32(Keys.ClipAudio.Projector.HEAD_COUNT, value)
+
     def add_xielu_alpha_p(self, values: Sequence[float]):
         self.add_array(Keys.xIELU.ALPHA_P, values)