tts : add native Higgs Audio v3 support v2 - extension for qwen3

[mirek190]

Overview

Continuation from
#24773

Adds a native llama.cpp-side Higgs Audio v3 TTS path around the Qwen3 backbone.

This includes:

• Higgs companion GGUF conversion/loading support
• native codebook sampling, RVQ, DAC, HuBERT/semantic/acoustic reference encoding pieces
• llama-tts/llama-higgs-tts/llama-higgs-reference-encode tooling
• /v1/audio/speech server wiring for Higgs speech generation
• focused Higgs unit/fixture tests and local documentation
• Implemented already existed CUDA col2im_1d with as suggest ServeurpersoCom

Models for test
https://huggingface.co/mirek190/higgs_v3_gguf/tree/main

Original model
https://huggingface.co/bosonai/higgs-audio-v3-tts-4b

for vulkan , cuda test - Model is fully multilanguage

llama-server.exe -m higgs-qwen3-backbone-q8_0.gguf --mmproj higgs-audio-f16.gguf --host 127.0.0.1 --port 8096 --device Vulkan1 -ngl 99 -c 1024 --parallel 1 --no-webui

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure:

[ggml-gh-bot]

Hi @mirek190, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• Multiple open PRs from a new contributor: We limit new contributors (those without a previously merged PR) to 1 open PR at a time. You currently have 2 open PRs.

• Large PR: Large changes require prior discussion (e.g. an issue or RFC) and maintainers may not be able to review this PR as-is. Consider splitting it into smaller, focused PRs.

---

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.

[mirek190]

Now is even faster

For sentence
"Adds a native llama.cpp-side Higgs Audio v3 TTS path around the Qwen3 backbone" - 6 seconds of audio

VULKAN
Higgs timing: prompt_decode=182.491 ms codebook=51.498 ms embed=1.431 ms step_decode=959.972 ms rvq=13.381 ms dac=194.013 ms stream_decode=0.000 ms steps=168 avg_step_decode=5.748 ms

CUDA
Higgs timing: prompt_decode=19.982 ms codebook=34.360 ms embed=1.395 ms step_decode=39.827 ms rvq=3.518 ms dac=206.493 ms stream_decode=0.000 ms steps=168 avg_step_decode=0.238 ms

[cmp-nct]

Too bad it's a commercial model, license is for "research".

[mirek190]

Too bad it's a commercial model, license is for "research".

yes but we have to start with something
Currently llamcpp is not supporting text input and audio output except ancient outie