Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254)

Browse Source 
* convert text model

* main model load ok

* convert encoder ok

* speaker encoder loading ok

* speaker enc graph

* adapt vocab for backbone (with some tricks)

* add suppress_tokens

* poc new mtmd gen api

* convert code_predictor to gguf

* load gen_code model ok

* add clip_encode

* wire up

* code gen cgraph init version

Co-authored-by: Pascal <admin@serveurperso.com>

* code2wav convert to gguf

* code2wav graph ok

* wire up in/out

* (wip) subgraph

* wire up

* wip, correct code2wav

* demo (to be removed)

* code2wav preserve kv between calls

* demo voice clone

* llama: add llama_model_get_tok_embd

* mtmd_helper_gen_audio API

* fix clamp cold prefix

Co-authored-by: Pascal <admin@serveurperso.com>

* fuse snake op

Co-authored-by: Pascal <admin@serveurperso.com>

* demo: use proper sampling

* update dev docs

* polymorphism helper

* revamp llama-tts binary

* update docs

* fix compile

* fix lint

* nits

* add guide + docs

* more timings info

* clean up code comments

* security fixes

* update docs

* use ggml_build_forward_select, clean up comments

* fix ci

* use ISO 639-1 language code

* rename CODE2WAV --> GEN_WAV, update docs

* clean up

* clean up tts.cpp

* add seq_id

* add step_prompt()

* mtmd_helper_model_can_chat

* clean up comments

---------

Co-authored-by: Pascal <admin@serveurperso.com>
This commit is contained in:
Xuan-Son Nguyen
2026-08-04 17:26:15 +02:00
committed by GitHub
co-authored by Pascal
parent 1c3c9674de
commit 0713275082
42 changed files with 3808 additions and 1895 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip-model.h
+106
View File
@@ -136,6 +136,19 @@ struct clip_hparams {
int32_t rvq_num_quantizers = 0;
std::vector<int32_t> rvq_codebook_size; // per-quantizer bin count (ragged, e.g. 1024/1024/256/128x17)
// qwen3tts code2wav
int32_t wav_tfm_n_layer = 0;
int32_t wav_tfm_n_embd = 0;
int32_t wav_tfm_n_ff = 0;
int32_t wav_tfm_n_head = 0;
int32_t wav_tfm_n_head_kv = 0;
float wav_tfm_eps = 1e-5f;
float wav_tfm_rope_theta = 10000.0f;
int32_t wav_upsample_n_block = 0;
int32_t wav_dac_n_block = 0;
int32_t wav_dac_n_res = 0;
int32_t wav_tfm_swa = 0; // pre_transformer's KV cache size, in frames
// mimo-v2.5: LLM-side connector (input_local_transformer)
int32_t audio_local_n_layer = 0;
int32_t audio_local_group_size = 0;
@@ -286,6 +299,14 @@ struct clip_layer {
ggml_tensor * cross_attn_norm_w = nullptr;
ggml_tensor * cross_attn_norm_b = nullptr;
// qwen3tts speaker encoder: SE-Res2Net block, tdnn1/tdnn2 reuse conv_pw1_w/b and conv_pw2_w/b above
ggml_tensor * se_conv1_w = nullptr;
ggml_tensor * se_conv1_b = nullptr;
ggml_tensor * se_conv2_w = nullptr;
ggml_tensor * se_conv2_b = nullptr;
std::vector<ggml_tensor *> res2_conv_w; // Res2Net hierarchical branches
std::vector<ggml_tensor *> res2_conv_b;
bool has_deepstack() const {
return deepstack_fc1_w != nullptr;
}
@@ -365,6 +386,73 @@ struct qf_block {
std::vector<clip_layer> qf_proj_layers;
};
// qwen3tts code2wav: RVQ codes -> raw PCM
struct clip_code2wav {
// "upsample" stage: one ConvNeXt block plus the causal ConvTranspose1d before it
struct upsample_block {
ggml_tensor * conv_w = nullptr; // causal ConvTranspose1d, 2x
ggml_tensor * conv_b = nullptr;
ggml_tensor * dwconv_w = nullptr; // depthwise causal conv, k=7
ggml_tensor * dwconv_b = nullptr;
ggml_tensor * norm_w = nullptr; // LayerNorm
ggml_tensor * norm_b = nullptr;
ggml_tensor * pw1_w = nullptr; // pointwise expand
ggml_tensor * pw1_b = nullptr;
ggml_tensor * pw2_w = nullptr; // pointwise project
ggml_tensor * pw2_b = nullptr;
ggml_tensor * gamma = nullptr; // layer scale
};
// one DAC residual unit: SnakeBeta -> dilated causal conv -> SnakeBeta -> pointwise causal conv
struct dac_res {
ggml_tensor * act1_alpha = nullptr;
ggml_tensor * act1_beta = nullptr;
ggml_tensor * conv1_w = nullptr;
ggml_tensor * conv1_b = nullptr;
ggml_tensor * act2_alpha = nullptr;
ggml_tensor * act2_beta = nullptr;
ggml_tensor * conv2_w = nullptr;
ggml_tensor * conv2_b = nullptr;
};
// one DAC upsample block (SnakeBeta -> causal ConvTranspose1d -> 3 residual units)
struct dac_block {
ggml_tensor * snake_alpha = nullptr;
ggml_tensor * snake_beta = nullptr;
ggml_tensor * conv_w = nullptr; // causal ConvTranspose1d
ggml_tensor * conv_b = nullptr;
std::vector<dac_res> res;
};
// quantizer: RVQ codebook decode
ggml_tensor * quant_first_in_w = nullptr; // semantic RVQ, in_proj (1x1 conv, loaded as 2D)
ggml_tensor * quant_first_out_w = nullptr;
ggml_tensor * quant_first_cb_w = nullptr; // codebook (1 layer)
ggml_tensor * quant_rest_in_w = nullptr; // acoustic RVQ
ggml_tensor * quant_rest_out_w = nullptr;
ggml_tensor * quant_rest_cb_w = nullptr; // codebooks, merged 3D [15, vocab, dim]
ggml_tensor * pre_conv_w = nullptr;
ggml_tensor * pre_conv_b = nullptr;
ggml_tensor * tfm_in_proj_w = nullptr;
ggml_tensor * tfm_in_proj_b = nullptr;
ggml_tensor * tfm_out_proj_w = nullptr;
ggml_tensor * tfm_out_proj_b = nullptr;
ggml_tensor * tfm_output_norm_w = nullptr;
std::vector<clip_layer> tfm_layers; // reuses the generic block fields (ln_1/attn/ln_2/ffn/ls_1/ls_2)
std::vector<upsample_block> upsample;
ggml_tensor * dac_entry_w = nullptr;
ggml_tensor * dac_entry_b = nullptr;
std::vector<dac_block> dac;
ggml_tensor * dac_post_snake_alpha = nullptr;
ggml_tensor * dac_post_snake_beta = nullptr;
ggml_tensor * dac_post_conv_w = nullptr;
ggml_tensor * dac_post_conv_b = nullptr;
};
struct clip_model {
clip_modality modality = CLIP_MODALITY_VISION;
projector_type proj_type = PROJECTOR_TYPE_MLP;
@@ -577,6 +665,24 @@ struct clip_model {
ggml_tensor * conv2d_3_w = nullptr;
ggml_tensor * conv2d_3_b = nullptr;
// qwen3tts speaker encoder (ECAPA-TDNN)
// reused tensors: stem conv is conv1d_1_w/b, feature aggregation is conv_out_w/b, output proj is mm_fc_w/b
ggml_tensor * spk_asp_attn_w = nullptr;
ggml_tensor * spk_asp_attn_b = nullptr;
ggml_tensor * spk_asp_tdnn_w = nullptr;
ggml_tensor * spk_asp_tdnn_b = nullptr;
// qwen3tts code_predictor
ggml_tensor * gen_code_proj_in_w = nullptr; // small_to_mtp_projection
ggml_tensor * gen_code_proj_in_b = nullptr;
ggml_tensor * gen_code_embd_w = nullptr; // per-codebook embedding, merged 3D
ggml_tensor * gen_code_head_w = nullptr; // per-codebook output head, merged 3D
ggml_tensor * gen_code_out_embd_w = nullptr; // codebook-0 embedding, fed back into the talker
ggml_tensor * gen_code_norm_w = nullptr; // final norm
// qwen3tts code2wav: RVQ codes -> raw PCM
clip_code2wav c2w;
// cogvlm
ggml_tensor * mm_post_fc_norm_w = nullptr;
ggml_tensor * mm_post_fc_norm_b = nullptr;