mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-31 09:42:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat(qwen-tts): add Qwen-tts backend (#8163)

Browse Source 
* feat(qwen-tts): add Qwen-tts backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update intel deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Drop flash-attn for cuda13

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2026-01-23 15:18:41 +01:00
committed by GitHub
parent ea51567b89
commit 923ebbb344
38 changed files with 996 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
.github/workflows/backend.yml vendored
View File

@@ -105,6 +105,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "9"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-qwen-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "9"
@@ -353,6 +366,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-qwen-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
@@ -431,6 +457,19 @@ jobs:
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-qwen-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
@@ -680,6 +719,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-qwen-tts'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
@@ -824,6 +876,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-qwen-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
@@ -890,6 +955,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-qwen-tts'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
@@ -1343,6 +1421,19 @@ jobs:
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-qwen-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""

21
.github/workflows/test-extra.yml vendored
View File

@@ -284,4 +284,23 @@ jobs:
- name: Test pocket-tts
run: |
make --jobs=5 --output-sync=target -C backend/python/pocket-tts
make --jobs=5 --output-sync=target -C backend/python/pocket-tts test
make --jobs=5 --output-sync=target -C backend/python/pocket-tts test
tests-qwen-tts:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test qwen-tts
run: |
make --jobs=5 --output-sync=target -C backend/python/qwen-tts
make --jobs=5 --output-sync=target -C backend/python/qwen-tts test