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.h
+29
View File
@@ -37,6 +37,7 @@ struct clip_image_f32_batch;
enum clip_modality {
CLIP_MODALITY_VISION,
CLIP_MODALITY_AUDIO,
CLIP_MODALITY_GEN_AUDIO,
};
enum clip_flash_attn_type {
@@ -61,6 +62,7 @@ struct clip_context_params {
struct clip_init_result {
struct clip_ctx * ctx_v; // vision context
struct clip_ctx * ctx_a; // audio context
struct clip_ctx * ctx_gen_a; // audio generation context
};
struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params);
@@ -84,6 +86,33 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx);
bool clip_image_encode (struct clip_ctx * ctx, int n_threads, const clip_image_f32 * img, std::vector<float> & out_vec);
bool clip_image_batch_encode(struct clip_ctx * ctx, int n_threads, const struct clip_image_f32_batch * imgs, std::vector<float> & out_batch_embd);
enum clip_gen_process_type {
CLIP_GEN_PROCESS_GEN_UNKNOWN,
CLIP_GEN_PROCESS_GEN_CODE, // h_state to codes
CLIP_GEN_PROCESS_GEN_WAV, // codes to raw PCM audio
};
struct clip_encode_params {
int n_threads = 1;
const clip_image_f32_batch * imgs = nullptr;
std::vector<float> * out_embd = nullptr;
// for audio gen, imgs has exactly one entry: hidden state from backbone (GEN_CODE) or unused (GEN_WAV)
clip_gen_process_type gen_process = CLIP_GEN_PROCESS_GEN_UNKNOWN;
// GEN_CODE: out_embd receives the embd to feed back to the backbone
int32_t code0 = 0; // semantic code sampled by the backbone
int32_t top_k = 50;
float top_p = 1.0f;
std::vector<int32_t> * out_codes = nullptr; // this frame's 16 sampled codes
// GEN_WAV
const std::vector<int32_t> * codes = nullptr; // this frame's 16 RVQ codes
std::vector<float> * out_audio = nullptr; // decoded PCM samples, F32
const std::vector<uint8_t> * state_in = nullptr; // state from previous call, null or wrong size means cold start
std::vector<uint8_t> * state_out = nullptr; // state for the next call
};
bool clip_encode(struct clip_ctx * ctx, struct clip_encode_params * params);
bool clip_is_llava(const struct clip_ctx * ctx);
// note for contributor: this clip_is_(model) pattern is deprecated
// do NOT add new functions like this