mirror of
https://github.com/mudler/LocalAI.git
synced 2026-02-06 12:43:04 -05:00
Compare commits
1 Commits
master
...
copilot/fi
| Author | SHA1 | Date | |
|---|---|---|---|
|
5041294265 |
348
.github/workflows/backend.yml
vendored
348
.github/workflows/backend.yml
vendored
@@ -14,7 +14,6 @@ concurrency:
|
||||
|
||||
jobs:
|
||||
backend-jobs:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
uses: ./.github/workflows/backend_build.yml
|
||||
with:
|
||||
tag-latest: ${{ matrix.tag-latest }}
|
||||
@@ -105,58 +104,6 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-ace-step'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'true'
|
||||
backend: "ace-step"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-mlx'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'true'
|
||||
backend: "mlx"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-mlx-vlm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'true'
|
||||
backend: "mlx-vlm"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-mlx-audio'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'true'
|
||||
backend: "mlx-audio"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
# CUDA 12 builds
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
@@ -301,19 +248,6 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12-ace-step'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "ace-step"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
@@ -366,19 +300,6 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12-outetts'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "outetts"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
@@ -405,45 +326,6 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12-mlx'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "mlx"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12-mlx-vlm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "mlx-vlm"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12-mlx-audio'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "mlx-audio"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "8"
|
||||
@@ -627,19 +509,6 @@ 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-ace-step'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "ace-step"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'l4t'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
@@ -705,45 +574,6 @@ jobs:
|
||||
backend: "diffusers"
|
||||
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-mlx'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
ubuntu-version: '2404'
|
||||
backend: "mlx"
|
||||
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-mlx-vlm'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
ubuntu-version: '2404'
|
||||
backend: "mlx-vlm"
|
||||
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-mlx-audio'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
ubuntu-version: '2404'
|
||||
backend: "mlx-audio"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
@@ -809,45 +639,6 @@ 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-mlx'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "mlx"
|
||||
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-mlx-vlm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "mlx-vlm"
|
||||
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-mlx-audio'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "mlx-audio"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
@@ -992,19 +783,6 @@ 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-ace-step'
|
||||
runs-on: 'arc-runner-set'
|
||||
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
|
||||
skip-drivers: 'false'
|
||||
backend: "ace-step"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
# ROCm additional backends
|
||||
- build-type: 'hipblas'
|
||||
cuda-major-version: ""
|
||||
@@ -1202,19 +980,6 @@ 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-ace-step'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "ace-step"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'l4t'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "0"
|
||||
@@ -1280,45 +1045,6 @@ 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-mlx'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
|
||||
skip-drivers: 'true'
|
||||
backend: "mlx"
|
||||
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-mlx-vlm'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
|
||||
skip-drivers: 'true'
|
||||
backend: "mlx-vlm"
|
||||
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-mlx-audio'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
|
||||
skip-drivers: 'true'
|
||||
backend: "mlx-audio"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2204'
|
||||
# SYCL additional backends
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
@@ -1836,19 +1562,6 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-outetts'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'true'
|
||||
backend: "outetts"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
backend-jobs-darwin:
|
||||
uses: ./.github/workflows/backend_build_darwin.yml
|
||||
strategy:
|
||||
@@ -1857,9 +1570,6 @@ jobs:
|
||||
- backend: "diffusers"
|
||||
tag-suffix: "-metal-darwin-arm64-diffusers"
|
||||
build-type: "mps"
|
||||
- backend: "ace-step"
|
||||
tag-suffix: "-metal-darwin-arm64-ace-step"
|
||||
build-type: "mps"
|
||||
- backend: "mlx"
|
||||
tag-suffix: "-metal-darwin-arm64-mlx"
|
||||
build-type: "mps"
|
||||
@@ -1880,64 +1590,6 @@ jobs:
|
||||
tag-suffix: "-metal-darwin-arm64-whisper"
|
||||
build-type: "metal"
|
||||
lang: "go"
|
||||
- backend: "vibevoice"
|
||||
tag-suffix: "-metal-darwin-arm64-vibevoice"
|
||||
build-type: "mps"
|
||||
- backend: "qwen-asr"
|
||||
tag-suffix: "-metal-darwin-arm64-qwen-asr"
|
||||
build-type: "mps"
|
||||
- backend: "qwen-tts"
|
||||
tag-suffix: "-metal-darwin-arm64-qwen-tts"
|
||||
build-type: "mps"
|
||||
- backend: "voxcpm"
|
||||
tag-suffix: "-metal-darwin-arm64-voxcpm"
|
||||
build-type: "mps"
|
||||
- backend: "pocket-tts"
|
||||
tag-suffix: "-metal-darwin-arm64-pocket-tts"
|
||||
build-type: "mps"
|
||||
- backend: "moonshine"
|
||||
tag-suffix: "-metal-darwin-arm64-moonshine"
|
||||
build-type: "mps"
|
||||
- backend: "whisperx"
|
||||
tag-suffix: "-metal-darwin-arm64-whisperx"
|
||||
build-type: "mps"
|
||||
- backend: "rerankers"
|
||||
tag-suffix: "-metal-darwin-arm64-rerankers"
|
||||
build-type: "mps"
|
||||
- backend: "transformers"
|
||||
tag-suffix: "-metal-darwin-arm64-transformers"
|
||||
build-type: "mps"
|
||||
- backend: "kokoro"
|
||||
tag-suffix: "-metal-darwin-arm64-kokoro"
|
||||
build-type: "mps"
|
||||
- backend: "faster-whisper"
|
||||
tag-suffix: "-metal-darwin-arm64-faster-whisper"
|
||||
build-type: "mps"
|
||||
- backend: "coqui"
|
||||
tag-suffix: "-metal-darwin-arm64-coqui"
|
||||
build-type: "mps"
|
||||
- backend: "rfdetr"
|
||||
tag-suffix: "-metal-darwin-arm64-rfdetr"
|
||||
build-type: "mps"
|
||||
- backend: "kitten-tts"
|
||||
tag-suffix: "-metal-darwin-arm64-kitten-tts"
|
||||
build-type: "mps"
|
||||
- backend: "piper"
|
||||
tag-suffix: "-metal-darwin-arm64-piper"
|
||||
build-type: "metal"
|
||||
lang: "go"
|
||||
- backend: "silero-vad"
|
||||
tag-suffix: "-metal-darwin-arm64-silero-vad"
|
||||
build-type: "metal"
|
||||
lang: "go"
|
||||
- backend: "local-store"
|
||||
tag-suffix: "-metal-darwin-arm64-local-store"
|
||||
build-type: "metal"
|
||||
lang: "go"
|
||||
- backend: "huggingface"
|
||||
tag-suffix: "-metal-darwin-arm64-huggingface"
|
||||
build-type: "metal"
|
||||
lang: "go"
|
||||
with:
|
||||
backend: ${{ matrix.backend }}
|
||||
build-type: ${{ matrix.build-type }}
|
||||
|
||||
1
.github/workflows/bump_deps.yaml
vendored
1
.github/workflows/bump_deps.yaml
vendored
@@ -5,7 +5,6 @@ on:
|
||||
workflow_dispatch:
|
||||
jobs:
|
||||
bump-backends:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
|
||||
1
.github/workflows/bump_docs.yaml
vendored
1
.github/workflows/bump_docs.yaml
vendored
@@ -5,7 +5,6 @@ on:
|
||||
workflow_dispatch:
|
||||
jobs:
|
||||
bump-docs:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
|
||||
1
.github/workflows/checksum_checker.yaml
vendored
1
.github/workflows/checksum_checker.yaml
vendored
@@ -5,7 +5,6 @@ on:
|
||||
workflow_dispatch:
|
||||
jobs:
|
||||
checksum_check:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Force Install GIT latest
|
||||
|
||||
2
.github/workflows/dependabot_auto.yml
vendored
2
.github/workflows/dependabot_auto.yml
vendored
@@ -9,8 +9,8 @@ permissions:
|
||||
|
||||
jobs:
|
||||
dependabot:
|
||||
if: github.repository == 'mudler/LocalAI' && github.actor == 'dependabot[bot]'
|
||||
runs-on: ubuntu-latest
|
||||
if: ${{ github.actor == 'dependabot[bot]' }}
|
||||
steps:
|
||||
- name: Dependabot metadata
|
||||
id: metadata
|
||||
|
||||
5
.github/workflows/deploy-explorer.yaml
vendored
5
.github/workflows/deploy-explorer.yaml
vendored
@@ -12,7 +12,6 @@ concurrency:
|
||||
|
||||
jobs:
|
||||
build-linux:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Clone
|
||||
@@ -34,7 +33,7 @@ jobs:
|
||||
run: |
|
||||
CGO_ENABLED=0 make build
|
||||
- name: rm
|
||||
uses: appleboy/ssh-action@v1.2.5
|
||||
uses: appleboy/ssh-action@v1.2.4
|
||||
with:
|
||||
host: ${{ secrets.EXPLORER_SSH_HOST }}
|
||||
username: ${{ secrets.EXPLORER_SSH_USERNAME }}
|
||||
@@ -54,7 +53,7 @@ jobs:
|
||||
rm: true
|
||||
target: ./local-ai
|
||||
- name: restarting
|
||||
uses: appleboy/ssh-action@v1.2.5
|
||||
uses: appleboy/ssh-action@v1.2.4
|
||||
with:
|
||||
host: ${{ secrets.EXPLORER_SSH_HOST }}
|
||||
username: ${{ secrets.EXPLORER_SSH_USERNAME }}
|
||||
|
||||
1
.github/workflows/gallery-agent.yaml
vendored
1
.github/workflows/gallery-agent.yaml
vendored
@@ -27,7 +27,6 @@ on:
|
||||
type: string
|
||||
jobs:
|
||||
gallery-agent:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
|
||||
1
.github/workflows/generate_grpc_cache.yaml
vendored
1
.github/workflows/generate_grpc_cache.yaml
vendored
@@ -13,7 +13,6 @@ concurrency:
|
||||
|
||||
jobs:
|
||||
generate_caches:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
|
||||
1
.github/workflows/generate_intel_image.yaml
vendored
1
.github/workflows/generate_intel_image.yaml
vendored
@@ -12,7 +12,6 @@ concurrency:
|
||||
|
||||
jobs:
|
||||
generate_caches:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
|
||||
3
.github/workflows/image.yml
vendored
3
.github/workflows/image.yml
vendored
@@ -14,7 +14,6 @@
|
||||
|
||||
jobs:
|
||||
hipblas-jobs:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
uses: ./.github/workflows/image_build.yml
|
||||
with:
|
||||
tag-latest: ${{ matrix.tag-latest }}
|
||||
@@ -51,7 +50,6 @@
|
||||
ubuntu-codename: 'noble'
|
||||
|
||||
core-image-build:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
uses: ./.github/workflows/image_build.yml
|
||||
with:
|
||||
tag-latest: ${{ matrix.tag-latest }}
|
||||
@@ -138,7 +136,6 @@
|
||||
ubuntu-codename: 'noble'
|
||||
|
||||
gh-runner:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
uses: ./.github/workflows/image_build.yml
|
||||
with:
|
||||
tag-latest: ${{ matrix.tag-latest }}
|
||||
|
||||
2
.github/workflows/localaibot_automerge.yml
vendored
2
.github/workflows/localaibot_automerge.yml
vendored
@@ -10,8 +10,8 @@ permissions:
|
||||
actions: write # to dispatch publish workflow
|
||||
jobs:
|
||||
dependabot:
|
||||
if: github.repository == 'mudler/LocalAI' && github.actor == 'localai-bot' && !contains(github.event.pull_request.title, 'chore(model gallery):')
|
||||
runs-on: ubuntu-latest
|
||||
if: ${{ github.actor == 'localai-bot' && !contains(github.event.pull_request.title, 'chore(model gallery):') }}
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v6
|
||||
|
||||
4
.github/workflows/notify-models.yaml
vendored
4
.github/workflows/notify-models.yaml
vendored
@@ -10,7 +10,7 @@ permissions:
|
||||
|
||||
jobs:
|
||||
notify-discord:
|
||||
if: github.repository == 'mudler/LocalAI' && (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model'))
|
||||
if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
|
||||
env:
|
||||
MODEL_NAME: gemma-3-12b-it-qat
|
||||
runs-on: ubuntu-latest
|
||||
@@ -90,7 +90,7 @@ jobs:
|
||||
connect-timeout-seconds: 180
|
||||
limit-access-to-actor: true
|
||||
notify-twitter:
|
||||
if: github.repository == 'mudler/LocalAI' && (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model'))
|
||||
if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
|
||||
env:
|
||||
MODEL_NAME: gemma-3-12b-it-qat
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
1
.github/workflows/notify-releases.yaml
vendored
1
.github/workflows/notify-releases.yaml
vendored
@@ -6,7 +6,6 @@ on:
|
||||
|
||||
jobs:
|
||||
notify-discord:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
RELEASE_BODY: ${{ github.event.release.body }}
|
||||
|
||||
1
.github/workflows/stalebot.yml
vendored
1
.github/workflows/stalebot.yml
vendored
@@ -8,7 +8,6 @@ on:
|
||||
|
||||
jobs:
|
||||
stale:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # v9
|
||||
|
||||
1
.github/workflows/update_swagger.yaml
vendored
1
.github/workflows/update_swagger.yaml
vendored
@@ -5,7 +5,6 @@ on:
|
||||
workflow_dispatch:
|
||||
jobs:
|
||||
swagger:
|
||||
if: github.repository == 'mudler/LocalAI'
|
||||
strategy:
|
||||
fail-fast: false
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
12
Makefile
12
Makefile
@@ -1,5 +1,5 @@
|
||||
# Disable parallel execution for backend builds
|
||||
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx backends/ace-step
|
||||
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx
|
||||
|
||||
GOCMD=go
|
||||
GOTEST=$(GOCMD) test
|
||||
@@ -308,7 +308,6 @@ protogen-go-clean:
|
||||
|
||||
prepare-test-extra: protogen-python
|
||||
$(MAKE) -C backend/python/transformers
|
||||
$(MAKE) -C backend/python/outetts
|
||||
$(MAKE) -C backend/python/diffusers
|
||||
$(MAKE) -C backend/python/chatterbox
|
||||
$(MAKE) -C backend/python/vllm
|
||||
@@ -320,11 +319,9 @@ prepare-test-extra: protogen-python
|
||||
$(MAKE) -C backend/python/qwen-asr
|
||||
$(MAKE) -C backend/python/voxcpm
|
||||
$(MAKE) -C backend/python/whisperx
|
||||
$(MAKE) -C backend/python/ace-step
|
||||
|
||||
test-extra: prepare-test-extra
|
||||
$(MAKE) -C backend/python/transformers test
|
||||
$(MAKE) -C backend/python/outetts test
|
||||
$(MAKE) -C backend/python/diffusers test
|
||||
$(MAKE) -C backend/python/chatterbox test
|
||||
$(MAKE) -C backend/python/vllm test
|
||||
@@ -336,7 +333,6 @@ test-extra: prepare-test-extra
|
||||
$(MAKE) -C backend/python/qwen-asr test
|
||||
$(MAKE) -C backend/python/voxcpm test
|
||||
$(MAKE) -C backend/python/whisperx test
|
||||
$(MAKE) -C backend/python/ace-step test
|
||||
|
||||
DOCKER_IMAGE?=local-ai
|
||||
DOCKER_AIO_IMAGE?=local-ai-aio
|
||||
@@ -455,7 +451,6 @@ BACKEND_WHISPER = whisper|golang|.|false|true
|
||||
# Python backends with root context
|
||||
BACKEND_RERANKERS = rerankers|python|.|false|true
|
||||
BACKEND_TRANSFORMERS = transformers|python|.|false|true
|
||||
BACKEND_OUTETTS = outetts|python|.|false|true
|
||||
BACKEND_FASTER_WHISPER = faster-whisper|python|.|false|true
|
||||
BACKEND_COQUI = coqui|python|.|false|true
|
||||
BACKEND_RFDETR = rfdetr|python|.|false|true
|
||||
@@ -473,7 +468,6 @@ BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
|
||||
BACKEND_QWEN_ASR = qwen-asr|python|.|false|true
|
||||
BACKEND_VOXCPM = voxcpm|python|.|false|true
|
||||
BACKEND_WHISPERX = whisperx|python|.|false|true
|
||||
BACKEND_ACE_STEP = ace-step|python|.|false|true
|
||||
|
||||
# Helper function to build docker image for a backend
|
||||
# Usage: $(call docker-build-backend,BACKEND_NAME,DOCKERFILE_TYPE,BUILD_CONTEXT,PROGRESS_FLAG,NEEDS_BACKEND_ARG)
|
||||
@@ -505,7 +499,6 @@ $(eval $(call generate-docker-build-target,$(BACKEND_STABLEDIFFUSION_GGML)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_WHISPER)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_RERANKERS)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_TRANSFORMERS)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_OUTETTS)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_FASTER_WHISPER)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_COQUI)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_RFDETR)))
|
||||
@@ -523,13 +516,12 @@ $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_QWEN_ASR)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
|
||||
$(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
|
||||
|
||||
# Pattern rule for docker-save targets
|
||||
docker-save-%: backend-images
|
||||
docker save local-ai-backend:$* -o backend-images/$*.tar
|
||||
|
||||
docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-voxcpm docker-build-whisperx docker-build-ace-step
|
||||
docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-voxcpm docker-build-whisperx
|
||||
|
||||
########################################################
|
||||
### Mock Backend for E2E Tests
|
||||
|
||||
13
README.md
13
README.md
@@ -203,8 +203,7 @@ local-ai run oci://localai/phi-2:latest
|
||||
For more information, see [💻 Getting started](https://localai.io/basics/getting_started/index.html), if you are interested in our roadmap items and future enhancements, you can see the [Issues labeled as Roadmap here](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
|
||||
|
||||
## 📰 Latest project news
|
||||
- February 2026: [Realtime API for audio-to-audio with tool calling](https://github.com/mudler/LocalAI/pull/6245), [ACE-Step 1.5 support](https://github.com/mudler/LocalAI/pull/8396)
|
||||
- January 2026: **LocalAI 3.10.0** - Major release with Anthropic API support, Open Responses API for stateful agents, video & image generation suite (LTX-2), unified GPU backends, tool streaming & XML parsing, system-aware backend gallery, crash fixes for AVX-only CPUs and AMD VRAM reporting, request tracing, and new backends: **Moonshine** (ultra-fast transcription), **Pocket-TTS** (lightweight TTS). Vulkan arm64 builds now available. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v3.10.0).
|
||||
|
||||
- December 2025: [Dynamic Memory Resource reclaimer](https://github.com/mudler/LocalAI/pull/7583), [Automatic fitting of models to multiple GPUS(llama.cpp)](https://github.com/mudler/LocalAI/pull/7584), [Added Vibevoice backend](https://github.com/mudler/LocalAI/pull/7494)
|
||||
- November 2025: Major improvements to the UX. Among these: [Import models via URL](https://github.com/mudler/LocalAI/pull/7245) and [Multiple chats and history](https://github.com/mudler/LocalAI/pull/7325)
|
||||
- October 2025: 🔌 [Model Context Protocol (MCP)](https://localai.io/docs/features/mcp/) support added for agentic capabilities with external tools
|
||||
@@ -270,7 +269,6 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
|
||||
|---------|-------------|---------------------|
|
||||
| **whisper.cpp** | OpenAI Whisper in C/C++ | CUDA 12/13, ROCm, Intel SYCL, Vulkan, CPU |
|
||||
| **faster-whisper** | Fast Whisper with CTranslate2 | CUDA 12/13, ROCm, Intel, CPU |
|
||||
| **moonshine** | Ultra-fast transcription engine for low-end devices | CUDA 12/13, Metal, CPU |
|
||||
| **coqui** | Advanced TTS with 1100+ languages | CUDA 12/13, ROCm, Intel, CPU |
|
||||
| **kokoro** | Lightweight TTS model | CUDA 12/13, ROCm, Intel, CPU |
|
||||
| **chatterbox** | Production-grade TTS | CUDA 12/13, CPU |
|
||||
@@ -281,7 +279,6 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
|
||||
| **vibevoice** | Real-time TTS with voice cloning | CUDA 12/13, ROCm, Intel, CPU |
|
||||
| **pocket-tts** | Lightweight CPU-based TTS | CUDA 12/13, ROCm, Intel, CPU |
|
||||
| **qwen-tts** | High-quality TTS with custom voice, voice design, and voice cloning | CUDA 12/13, ROCm, Intel, CPU |
|
||||
| **ace-step** | Music generation from text descriptions, lyrics, or audio samples | CUDA 12/13, ROCm, Intel, Metal, CPU |
|
||||
|
||||
### Image & Video Generation
|
||||
| Backend | Description | Acceleration Support |
|
||||
@@ -303,11 +300,11 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
|
||||
|-------------------|-------------------|------------------|
|
||||
| **NVIDIA CUDA 12** | All CUDA-compatible backends | Nvidia hardware |
|
||||
| **NVIDIA CUDA 13** | All CUDA-compatible backends | Nvidia hardware |
|
||||
| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, neutts, vibevoice, pocket-tts, qwen-tts, ace-step | AMD Graphics |
|
||||
| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, coqui, kokoro, vibevoice, pocket-tts, qwen-tts, ace-step | Intel Arc, Intel iGPUs |
|
||||
| **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM, moonshine, ace-step | Apple M1/M2/M3+ |
|
||||
| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, neutts, vibevoice, pocket-tts, qwen-tts | AMD Graphics |
|
||||
| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, coqui, kokoro, vibevoice, pocket-tts, qwen-tts | Intel Arc, Intel iGPUs |
|
||||
| **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM | Apple M1/M2/M3+ |
|
||||
| **Vulkan** | llama.cpp, whisper, stablediffusion | Cross-platform GPUs |
|
||||
| **NVIDIA Jetson (CUDA 12)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr, ace-step | ARM64 embedded AI (AGX Orin, etc.) |
|
||||
| **NVIDIA Jetson (CUDA 12)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr | ARM64 embedded AI (AGX Orin, etc.) |
|
||||
| **NVIDIA Jetson (CUDA 13)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr | ARM64 embedded AI (DGX Spark) |
|
||||
| **CPU Optimized** | All backends | AVX/AVX2/AVX512, quantization support |
|
||||
|
||||
|
||||
@@ -365,14 +365,6 @@ message SoundGenerationRequest {
|
||||
optional bool sample = 6;
|
||||
optional string src = 7;
|
||||
optional int32 src_divisor = 8;
|
||||
optional bool think = 9;
|
||||
optional string caption = 10;
|
||||
optional string lyrics = 11;
|
||||
optional int32 bpm = 12;
|
||||
optional string keyscale = 13;
|
||||
optional string language = 14;
|
||||
optional string timesignature = 15;
|
||||
optional bool instrumental = 17;
|
||||
}
|
||||
|
||||
message TokenizationResponse {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
|
||||
LLAMA_VERSION?=22cae832188a1f08d18bd0a707a4ba5cd03c7349
|
||||
LLAMA_VERSION?=2634ed207a17db1a54bd8df0555bd8499a6ab691
|
||||
LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
|
||||
|
||||
CMAKE_ARGS?=
|
||||
|
||||
@@ -7,6 +7,3 @@ package:
|
||||
bash package.sh
|
||||
|
||||
build: huggingface package
|
||||
|
||||
clean:
|
||||
rm -f huggingface
|
||||
@@ -8,5 +8,5 @@ set -e
|
||||
CURDIR=$(dirname "$(realpath $0)")
|
||||
|
||||
mkdir -p $CURDIR/package
|
||||
cp -avf $CURDIR/huggingface $CURDIR/package/
|
||||
cp -avrf $CURDIR/huggingface $CURDIR/package/
|
||||
cp -rfv $CURDIR/run.sh $CURDIR/package/
|
||||
@@ -7,6 +7,3 @@ package:
|
||||
bash package.sh
|
||||
|
||||
build: local-store package
|
||||
|
||||
clean:
|
||||
rm -f local-store
|
||||
@@ -8,5 +8,5 @@ set -e
|
||||
CURDIR=$(dirname "$(realpath $0)")
|
||||
|
||||
mkdir -p $CURDIR/package
|
||||
cp -avf $CURDIR/local-store $CURDIR/package/
|
||||
cp -avrf $CURDIR/local-store $CURDIR/package/
|
||||
cp -rfv $CURDIR/run.sh $CURDIR/package/
|
||||
@@ -35,6 +35,3 @@ package:
|
||||
bash package.sh
|
||||
|
||||
build: piper package
|
||||
|
||||
clean:
|
||||
rm -f piper
|
||||
@@ -10,8 +10,8 @@ CURDIR=$(dirname "$(realpath $0)")
|
||||
# Create lib directory
|
||||
mkdir -p $CURDIR/package/lib
|
||||
|
||||
cp -avf $CURDIR/piper $CURDIR/package/
|
||||
cp -avf $CURDIR/espeak-ng-data $CURDIR/package/
|
||||
cp -avrf $CURDIR/piper $CURDIR/package/
|
||||
cp -avrf $CURDIR/espeak-ng-data $CURDIR/package/
|
||||
cp -rfv $CURDIR/run.sh $CURDIR/package/
|
||||
cp -rfLv $CURDIR/sources/go-piper/piper-phonemize/pi/lib/* $CURDIR/package/lib/
|
||||
|
||||
|
||||
@@ -45,6 +45,3 @@ package:
|
||||
bash package.sh
|
||||
|
||||
build: silero-vad package
|
||||
|
||||
clean:
|
||||
rm -f silero-vad
|
||||
@@ -10,8 +10,8 @@ CURDIR=$(dirname "$(realpath $0)")
|
||||
# Create lib directory
|
||||
mkdir -p $CURDIR/package/lib
|
||||
|
||||
cp -avf $CURDIR/silero-vad $CURDIR/package/
|
||||
cp -avf $CURDIR/run.sh $CURDIR/package/
|
||||
cp -avrf $CURDIR/silero-vad $CURDIR/package/
|
||||
cp -avrf $CURDIR/run.sh $CURDIR/package/
|
||||
cp -rfLv $CURDIR/backend-assets/lib/* $CURDIR/package/lib/
|
||||
|
||||
# Detect architecture and copy appropriate libraries
|
||||
|
||||
@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
|
||||
|
||||
# whisper.cpp version
|
||||
WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
|
||||
WHISPER_CPP_VERSION?=941bdabbe4561bc6de68981aea01bc5ab05781c5
|
||||
WHISPER_CPP_VERSION?=aa1bc0d1a6dfd70dbb9f60c11df12441e03a9075
|
||||
SO_TARGET?=libgowhisper.so
|
||||
|
||||
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
|
||||
@@ -78,7 +78,7 @@ package: whisper
|
||||
build: package
|
||||
|
||||
clean: purge
|
||||
rm -rf libgowhisper*.so package sources/whisper.cpp whisper
|
||||
rm -rf libgowhisper*.so sources/whisper.cpp whisper
|
||||
|
||||
purge:
|
||||
rm -rf build*
|
||||
|
||||
@@ -105,7 +105,6 @@
|
||||
intel: "intel-rfdetr"
|
||||
#amd: "rocm-rfdetr"
|
||||
nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
|
||||
metal: "metal-rfdetr"
|
||||
default: "cpu-rfdetr"
|
||||
nvidia-cuda-13: "cuda13-rfdetr"
|
||||
nvidia-cuda-12: "cuda12-rfdetr"
|
||||
@@ -183,15 +182,6 @@
|
||||
- text-to-text
|
||||
- LLM
|
||||
- MLX
|
||||
capabilities:
|
||||
default: "cpu-mlx"
|
||||
nvidia: "cuda12-mlx"
|
||||
metal: "metal-mlx"
|
||||
nvidia-cuda-12: "cuda12-mlx"
|
||||
nvidia-cuda-13: "cuda13-mlx"
|
||||
nvidia-l4t: "nvidia-l4t-mlx"
|
||||
nvidia-l4t-cuda-12: "nvidia-l4t-mlx"
|
||||
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx"
|
||||
- &mlx-vlm
|
||||
name: "mlx-vlm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-vlm"
|
||||
@@ -209,15 +199,6 @@
|
||||
- vision-language
|
||||
- LLM
|
||||
- MLX
|
||||
capabilities:
|
||||
default: "cpu-mlx-vlm"
|
||||
nvidia: "cuda12-mlx-vlm"
|
||||
metal: "metal-mlx-vlm"
|
||||
nvidia-cuda-12: "cuda12-mlx-vlm"
|
||||
nvidia-cuda-13: "cuda13-mlx-vlm"
|
||||
nvidia-l4t: "nvidia-l4t-mlx-vlm"
|
||||
nvidia-l4t-cuda-12: "nvidia-l4t-mlx-vlm"
|
||||
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-vlm"
|
||||
- &mlx-audio
|
||||
name: "mlx-audio"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-audio"
|
||||
@@ -235,15 +216,6 @@
|
||||
- text-to-audio
|
||||
- LLM
|
||||
- MLX
|
||||
capabilities:
|
||||
default: "cpu-mlx-audio"
|
||||
nvidia: "cuda12-mlx-audio"
|
||||
metal: "metal-mlx-audio"
|
||||
nvidia-cuda-12: "cuda12-mlx-audio"
|
||||
nvidia-cuda-13: "cuda13-mlx-audio"
|
||||
nvidia-l4t: "nvidia-l4t-mlx-audio"
|
||||
nvidia-l4t-cuda-12: "nvidia-l4t-mlx-audio"
|
||||
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-audio"
|
||||
- &rerankers
|
||||
name: "rerankers"
|
||||
alias: "rerankers"
|
||||
@@ -251,7 +223,6 @@
|
||||
nvidia: "cuda12-rerankers"
|
||||
intel: "intel-rerankers"
|
||||
amd: "rocm-rerankers"
|
||||
metal: "metal-rerankers"
|
||||
- &transformers
|
||||
name: "transformers"
|
||||
icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4
|
||||
@@ -269,7 +240,6 @@
|
||||
nvidia: "cuda12-transformers"
|
||||
intel: "intel-transformers"
|
||||
amd: "rocm-transformers"
|
||||
metal: "metal-transformers"
|
||||
nvidia-cuda-13: "cuda13-transformers"
|
||||
nvidia-cuda-12: "cuda12-transformers"
|
||||
- &diffusers
|
||||
@@ -296,34 +266,6 @@
|
||||
nvidia-cuda-12: "cuda12-diffusers"
|
||||
nvidia-l4t-cuda-12: "nvidia-l4t-arm64-diffusers"
|
||||
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-diffusers"
|
||||
- &ace-step
|
||||
name: "ace-step"
|
||||
description: |
|
||||
ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio).
|
||||
urls:
|
||||
- https://github.com/ace-step/ACE-Step-1.5
|
||||
tags:
|
||||
- music-generation
|
||||
- sound-generation
|
||||
alias: "ace-step"
|
||||
capabilities:
|
||||
nvidia: "cuda12-ace-step"
|
||||
intel: "intel-ace-step"
|
||||
amd: "rocm-ace-step"
|
||||
metal: "metal-ace-step"
|
||||
default: "cpu-ace-step"
|
||||
nvidia-cuda-13: "cuda13-ace-step"
|
||||
nvidia-cuda-12: "cuda12-ace-step"
|
||||
- !!merge <<: *ace-step
|
||||
name: "ace-step-development"
|
||||
capabilities:
|
||||
nvidia: "cuda12-ace-step-development"
|
||||
intel: "intel-ace-step-development"
|
||||
amd: "rocm-ace-step-development"
|
||||
metal: "metal-ace-step-development"
|
||||
default: "cpu-ace-step-development"
|
||||
nvidia-cuda-13: "cuda13-ace-step-development"
|
||||
nvidia-cuda-12: "cuda12-ace-step-development"
|
||||
- &faster-whisper
|
||||
icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
|
||||
description: |
|
||||
@@ -340,7 +282,6 @@
|
||||
nvidia: "cuda12-faster-whisper"
|
||||
intel: "intel-faster-whisper"
|
||||
amd: "rocm-faster-whisper"
|
||||
metal: "metal-faster-whisper"
|
||||
nvidia-cuda-13: "cuda13-faster-whisper"
|
||||
nvidia-cuda-12: "cuda12-faster-whisper"
|
||||
- &moonshine
|
||||
@@ -358,7 +299,6 @@
|
||||
alias: "moonshine"
|
||||
capabilities:
|
||||
nvidia: "cuda12-moonshine"
|
||||
metal: "metal-moonshine"
|
||||
default: "cpu-moonshine"
|
||||
nvidia-cuda-13: "cuda13-moonshine"
|
||||
nvidia-cuda-12: "cuda12-moonshine"
|
||||
@@ -378,7 +318,6 @@
|
||||
capabilities:
|
||||
nvidia: "cuda12-whisperx"
|
||||
amd: "rocm-whisperx"
|
||||
metal: "metal-whisperx"
|
||||
default: "cpu-whisperx"
|
||||
nvidia-cuda-13: "cuda13-whisperx"
|
||||
nvidia-cuda-12: "cuda12-whisperx"
|
||||
@@ -401,7 +340,6 @@
|
||||
intel: "intel-kokoro"
|
||||
amd: "rocm-kokoro"
|
||||
nvidia-l4t: "nvidia-l4t-kokoro"
|
||||
metal: "metal-kokoro"
|
||||
nvidia-cuda-13: "cuda13-kokoro"
|
||||
nvidia-cuda-12: "cuda12-kokoro"
|
||||
nvidia-l4t-cuda-12: "nvidia-l4t-arm64-kokoro"
|
||||
@@ -426,25 +364,9 @@
|
||||
nvidia: "cuda12-coqui"
|
||||
intel: "intel-coqui"
|
||||
amd: "rocm-coqui"
|
||||
metal: "metal-coqui"
|
||||
nvidia-cuda-13: "cuda13-coqui"
|
||||
nvidia-cuda-12: "cuda12-coqui"
|
||||
icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4
|
||||
- &outetts
|
||||
urls:
|
||||
- https://github.com/OuteAI/outetts
|
||||
description: |
|
||||
OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B).
|
||||
Supports custom speaker voices via audio path or default speakers.
|
||||
tags:
|
||||
- text-to-speech
|
||||
- TTS
|
||||
license: apache-2.0
|
||||
name: "outetts"
|
||||
alias: "outetts"
|
||||
capabilities:
|
||||
default: "cpu-outetts"
|
||||
nvidia-cuda-12: "cuda12-outetts"
|
||||
- &chatterbox
|
||||
urls:
|
||||
- https://github.com/resemble-ai/chatterbox
|
||||
@@ -483,7 +405,6 @@
|
||||
intel: "intel-vibevoice"
|
||||
amd: "rocm-vibevoice"
|
||||
nvidia-l4t: "nvidia-l4t-vibevoice"
|
||||
metal: "metal-vibevoice"
|
||||
default: "cpu-vibevoice"
|
||||
nvidia-cuda-13: "cuda13-vibevoice"
|
||||
nvidia-cuda-12: "cuda12-vibevoice"
|
||||
@@ -506,7 +427,6 @@
|
||||
intel: "intel-qwen-tts"
|
||||
amd: "rocm-qwen-tts"
|
||||
nvidia-l4t: "nvidia-l4t-qwen-tts"
|
||||
metal: "metal-qwen-tts"
|
||||
default: "cpu-qwen-tts"
|
||||
nvidia-cuda-13: "cuda13-qwen-tts"
|
||||
nvidia-cuda-12: "cuda12-qwen-tts"
|
||||
@@ -529,7 +449,6 @@
|
||||
intel: "intel-qwen-asr"
|
||||
amd: "rocm-qwen-asr"
|
||||
nvidia-l4t: "nvidia-l4t-qwen-asr"
|
||||
metal: "metal-qwen-asr"
|
||||
default: "cpu-qwen-asr"
|
||||
nvidia-cuda-13: "cuda13-qwen-asr"
|
||||
nvidia-cuda-12: "cuda12-qwen-asr"
|
||||
@@ -551,7 +470,6 @@
|
||||
nvidia: "cuda12-voxcpm"
|
||||
intel: "intel-voxcpm"
|
||||
amd: "rocm-voxcpm"
|
||||
metal: "metal-voxcpm"
|
||||
default: "cpu-voxcpm"
|
||||
nvidia-cuda-13: "cuda13-voxcpm"
|
||||
nvidia-cuda-12: "cuda12-voxcpm"
|
||||
@@ -572,7 +490,6 @@
|
||||
intel: "intel-pocket-tts"
|
||||
amd: "rocm-pocket-tts"
|
||||
nvidia-l4t: "nvidia-l4t-pocket-tts"
|
||||
metal: "metal-pocket-tts"
|
||||
default: "cpu-pocket-tts"
|
||||
nvidia-cuda-13: "cuda13-pocket-tts"
|
||||
nvidia-cuda-12: "cuda12-pocket-tts"
|
||||
@@ -733,234 +650,31 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-mlx-audio
|
||||
## mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cpu-mlx"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cpu-mlx-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cuda12-mlx"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cuda12-mlx-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cuda13-mlx"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cuda13-mlx-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "nvidia-l4t-mlx"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "nvidia-l4t-mlx-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cuda13-nvidia-l4t-arm64-mlx"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx
|
||||
- !!merge <<: *mlx
|
||||
name: "cuda13-nvidia-l4t-arm64-mlx-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx
|
||||
## mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cpu-mlx-vlm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cpu-mlx-vlm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cuda12-mlx-vlm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cuda12-mlx-vlm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cuda13-mlx-vlm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cuda13-mlx-vlm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "nvidia-l4t-mlx-vlm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "nvidia-l4t-mlx-vlm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cuda13-nvidia-l4t-arm64-mlx-vlm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm
|
||||
- !!merge <<: *mlx-vlm
|
||||
name: "cuda13-nvidia-l4t-arm64-mlx-vlm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm
|
||||
## mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cpu-mlx-audio"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cpu-mlx-audio-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cuda12-mlx-audio"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cuda12-mlx-audio-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cuda13-mlx-audio"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cuda13-mlx-audio-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "nvidia-l4t-mlx-audio"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "nvidia-l4t-mlx-audio-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cuda13-nvidia-l4t-arm64-mlx-audio"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio
|
||||
- !!merge <<: *mlx-audio
|
||||
name: "cuda13-nvidia-l4t-arm64-mlx-audio-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio
|
||||
- !!merge <<: *kitten-tts
|
||||
name: "kitten-tts-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-kitten-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-kitten-tts
|
||||
- !!merge <<: *kitten-tts
|
||||
name: "metal-kitten-tts"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kitten-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-kitten-tts
|
||||
- !!merge <<: *kitten-tts
|
||||
name: "metal-kitten-tts-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kitten-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-kitten-tts
|
||||
- !!merge <<: *huggingface
|
||||
name: "huggingface-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-huggingface"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-huggingface
|
||||
- !!merge <<: *huggingface
|
||||
name: "metal-huggingface"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-huggingface"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-huggingface
|
||||
- !!merge <<: *huggingface
|
||||
name: "metal-huggingface-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-huggingface"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-huggingface
|
||||
- !!merge <<: *local-store
|
||||
name: "local-store-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-local-store"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-local-store
|
||||
- !!merge <<: *local-store
|
||||
name: "metal-local-store"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-local-store"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-local-store
|
||||
- !!merge <<: *local-store
|
||||
name: "metal-local-store-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-local-store"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-local-store
|
||||
- !!merge <<: *silero-vad
|
||||
name: "silero-vad-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-silero-vad"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-silero-vad
|
||||
- !!merge <<: *silero-vad
|
||||
name: "metal-silero-vad"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-silero-vad"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-silero-vad
|
||||
- !!merge <<: *silero-vad
|
||||
name: "metal-silero-vad-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-silero-vad"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-silero-vad
|
||||
- !!merge <<: *piper
|
||||
name: "piper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-piper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-piper
|
||||
- !!merge <<: *piper
|
||||
name: "metal-piper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-piper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-piper
|
||||
- !!merge <<: *piper
|
||||
name: "metal-piper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-piper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-piper
|
||||
## llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "nvidia-l4t-arm64-llama-cpp"
|
||||
@@ -1334,7 +1048,6 @@
|
||||
intel: "intel-rfdetr-development"
|
||||
#amd: "rocm-rfdetr-development"
|
||||
nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
|
||||
metal: "metal-rfdetr-development"
|
||||
default: "cpu-rfdetr-development"
|
||||
nvidia-cuda-13: "cuda13-rfdetr-development"
|
||||
- !!merge <<: *rfdetr
|
||||
@@ -1402,16 +1115,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rfdetr"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-rfdetr
|
||||
- !!merge <<: *rfdetr
|
||||
name: "metal-rfdetr"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rfdetr"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-rfdetr
|
||||
- !!merge <<: *rfdetr
|
||||
name: "metal-rfdetr-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rfdetr"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-rfdetr
|
||||
## Rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "rerankers-development"
|
||||
@@ -1419,7 +1122,6 @@
|
||||
nvidia: "cuda12-rerankers-development"
|
||||
intel: "intel-rerankers-development"
|
||||
amd: "rocm-rerankers-development"
|
||||
metal: "metal-rerankers-development"
|
||||
nvidia-cuda-13: "cuda13-rerankers-development"
|
||||
- !!merge <<: *rerankers
|
||||
name: "cuda12-rerankers"
|
||||
@@ -1461,16 +1163,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "metal-rerankers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "metal-rerankers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-rerankers
|
||||
## Transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "transformers-development"
|
||||
@@ -1478,7 +1170,6 @@
|
||||
nvidia: "cuda12-transformers-development"
|
||||
intel: "intel-transformers-development"
|
||||
amd: "rocm-transformers-development"
|
||||
metal: "metal-transformers-development"
|
||||
nvidia-cuda-13: "cuda13-transformers-development"
|
||||
- !!merge <<: *transformers
|
||||
name: "cuda12-transformers"
|
||||
@@ -1520,16 +1211,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "metal-transformers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "metal-transformers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-transformers
|
||||
## Diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "diffusers-development"
|
||||
@@ -1621,67 +1302,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-diffusers
|
||||
## ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "cpu-ace-step"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "cpu-ace-step-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "cuda12-ace-step"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "cuda12-ace-step-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "cuda13-ace-step"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-13-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "cuda13-ace-step-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "rocm-ace-step"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "rocm-ace-step-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "intel-ace-step"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "intel-ace-step-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "metal-ace-step"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-ace-step
|
||||
- !!merge <<: *ace-step
|
||||
name: "metal-ace-step-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ace-step"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-ace-step
|
||||
## kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "kokoro-development"
|
||||
@@ -1690,7 +1310,6 @@
|
||||
intel: "intel-kokoro-development"
|
||||
amd: "rocm-kokoro-development"
|
||||
nvidia-l4t: "nvidia-l4t-kokoro-development"
|
||||
metal: "metal-kokoro-development"
|
||||
- !!merge <<: *kokoro
|
||||
name: "cuda12-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro"
|
||||
@@ -1741,16 +1360,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "metal-kokoro"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "metal-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-kokoro
|
||||
## faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "faster-whisper-development"
|
||||
@@ -1758,7 +1367,6 @@
|
||||
nvidia: "cuda12-faster-whisper-development"
|
||||
intel: "intel-faster-whisper-development"
|
||||
amd: "rocm-faster-whisper-development"
|
||||
metal: "metal-faster-whisper-development"
|
||||
nvidia-cuda-13: "cuda13-faster-whisper-development"
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "cuda12-faster-whisper-development"
|
||||
@@ -1790,16 +1398,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "metal-faster-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "metal-faster-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-faster-whisper
|
||||
## moonshine
|
||||
- !!merge <<: *moonshine
|
||||
name: "moonshine-development"
|
||||
@@ -1838,23 +1436,12 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moonshine"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-moonshine
|
||||
- !!merge <<: *moonshine
|
||||
name: "metal-moonshine"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-moonshine"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-moonshine
|
||||
- !!merge <<: *moonshine
|
||||
name: "metal-moonshine-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-moonshine"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-moonshine
|
||||
## whisperx
|
||||
- !!merge <<: *whisperx
|
||||
name: "whisperx-development"
|
||||
capabilities:
|
||||
nvidia: "cuda12-whisperx-development"
|
||||
amd: "rocm-whisperx-development"
|
||||
metal: "metal-whisperx-development"
|
||||
default: "cpu-whisperx-development"
|
||||
nvidia-cuda-13: "cuda13-whisperx-development"
|
||||
nvidia-cuda-12: "cuda12-whisperx-development"
|
||||
@@ -1898,16 +1485,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisperx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-13-whisperx
|
||||
- !!merge <<: *whisperx
|
||||
name: "metal-whisperx"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisperx"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-whisperx
|
||||
- !!merge <<: *whisperx
|
||||
name: "metal-whisperx-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisperx"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-whisperx
|
||||
## coqui
|
||||
|
||||
- !!merge <<: *coqui
|
||||
@@ -1916,7 +1493,6 @@
|
||||
nvidia: "cuda12-coqui-development"
|
||||
intel: "intel-coqui-development"
|
||||
amd: "rocm-coqui-development"
|
||||
metal: "metal-coqui-development"
|
||||
- !!merge <<: *coqui
|
||||
name: "cuda12-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-coqui"
|
||||
@@ -1947,42 +1523,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "metal-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "metal-coqui-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-coqui
|
||||
## outetts
|
||||
- !!merge <<: *outetts
|
||||
name: "outetts-development"
|
||||
capabilities:
|
||||
default: "cpu-outetts-development"
|
||||
nvidia-cuda-12: "cuda12-outetts-development"
|
||||
- !!merge <<: *outetts
|
||||
name: "cpu-outetts"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-outetts"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-outetts
|
||||
- !!merge <<: *outetts
|
||||
name: "cpu-outetts-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-outetts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-outetts
|
||||
- !!merge <<: *outetts
|
||||
name: "cuda12-outetts"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-outetts"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-outetts
|
||||
- !!merge <<: *outetts
|
||||
name: "cuda12-outetts-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-outetts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-outetts
|
||||
## chatterbox
|
||||
- !!merge <<: *chatterbox
|
||||
name: "chatterbox-development"
|
||||
@@ -2063,7 +1603,6 @@
|
||||
intel: "intel-vibevoice-development"
|
||||
amd: "rocm-vibevoice-development"
|
||||
nvidia-l4t: "nvidia-l4t-vibevoice-development"
|
||||
metal: "metal-vibevoice-development"
|
||||
default: "cpu-vibevoice-development"
|
||||
nvidia-cuda-13: "cuda13-vibevoice-development"
|
||||
nvidia-cuda-12: "cuda12-vibevoice-development"
|
||||
@@ -2139,16 +1678,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice
|
||||
- !!merge <<: *vibevoice
|
||||
name: "metal-vibevoice"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vibevoice"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-vibevoice
|
||||
- !!merge <<: *vibevoice
|
||||
name: "metal-vibevoice-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vibevoice"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-vibevoice
|
||||
## qwen-tts
|
||||
- !!merge <<: *qwen-tts
|
||||
name: "qwen-tts-development"
|
||||
@@ -2157,7 +1686,6 @@
|
||||
intel: "intel-qwen-tts-development"
|
||||
amd: "rocm-qwen-tts-development"
|
||||
nvidia-l4t: "nvidia-l4t-qwen-tts-development"
|
||||
metal: "metal-qwen-tts-development"
|
||||
default: "cpu-qwen-tts-development"
|
||||
nvidia-cuda-13: "cuda13-qwen-tts-development"
|
||||
nvidia-cuda-12: "cuda12-qwen-tts-development"
|
||||
@@ -2233,16 +1761,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts
|
||||
- !!merge <<: *qwen-tts
|
||||
name: "metal-qwen-tts"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-qwen-tts
|
||||
- !!merge <<: *qwen-tts
|
||||
name: "metal-qwen-tts-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-qwen-tts
|
||||
## qwen-asr
|
||||
- !!merge <<: *qwen-asr
|
||||
name: "qwen-asr-development"
|
||||
@@ -2251,7 +1769,6 @@
|
||||
intel: "intel-qwen-asr-development"
|
||||
amd: "rocm-qwen-asr-development"
|
||||
nvidia-l4t: "nvidia-l4t-qwen-asr-development"
|
||||
metal: "metal-qwen-asr-development"
|
||||
default: "cpu-qwen-asr-development"
|
||||
nvidia-cuda-13: "cuda13-qwen-asr-development"
|
||||
nvidia-cuda-12: "cuda12-qwen-asr-development"
|
||||
@@ -2327,16 +1844,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr
|
||||
- !!merge <<: *qwen-asr
|
||||
name: "metal-qwen-asr"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-asr"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-qwen-asr
|
||||
- !!merge <<: *qwen-asr
|
||||
name: "metal-qwen-asr-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-asr"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-qwen-asr
|
||||
## voxcpm
|
||||
- !!merge <<: *voxcpm
|
||||
name: "voxcpm-development"
|
||||
@@ -2344,7 +1851,6 @@
|
||||
nvidia: "cuda12-voxcpm-development"
|
||||
intel: "intel-voxcpm-development"
|
||||
amd: "rocm-voxcpm-development"
|
||||
metal: "metal-voxcpm-development"
|
||||
default: "cpu-voxcpm-development"
|
||||
nvidia-cuda-13: "cuda13-voxcpm-development"
|
||||
nvidia-cuda-12: "cuda12-voxcpm-development"
|
||||
@@ -2398,16 +1904,6 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-voxcpm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-voxcpm
|
||||
- !!merge <<: *voxcpm
|
||||
name: "metal-voxcpm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voxcpm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-voxcpm
|
||||
- !!merge <<: *voxcpm
|
||||
name: "metal-voxcpm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voxcpm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-voxcpm
|
||||
## pocket-tts
|
||||
- !!merge <<: *pocket-tts
|
||||
name: "pocket-tts-development"
|
||||
@@ -2416,7 +1912,6 @@
|
||||
intel: "intel-pocket-tts-development"
|
||||
amd: "rocm-pocket-tts-development"
|
||||
nvidia-l4t: "nvidia-l4t-pocket-tts-development"
|
||||
metal: "metal-pocket-tts-development"
|
||||
default: "cpu-pocket-tts-development"
|
||||
nvidia-cuda-13: "cuda13-pocket-tts-development"
|
||||
nvidia-cuda-12: "cuda12-pocket-tts-development"
|
||||
@@ -2492,13 +1987,3 @@
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts
|
||||
- !!merge <<: *pocket-tts
|
||||
name: "metal-pocket-tts"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-pocket-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-pocket-tts
|
||||
- !!merge <<: *pocket-tts
|
||||
name: "metal-pocket-tts-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-pocket-tts"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-pocket-tts
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
.DEFAULT_GOAL := install
|
||||
|
||||
.PHONY: install
|
||||
install:
|
||||
bash install.sh
|
||||
|
||||
.PHONY: protogen-clean
|
||||
protogen-clean:
|
||||
$(RM) backend_pb2_grpc.py backend_pb2.py
|
||||
|
||||
.PHONY: clean
|
||||
clean: protogen-clean
|
||||
rm -rf venv __pycache__
|
||||
|
||||
test: install
|
||||
bash test.sh
|
||||
@@ -1,472 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
LocalAI ACE-Step Backend
|
||||
|
||||
gRPC backend for ACE-Step 1.5 music generation. Aligns with upstream acestep API:
|
||||
- LoadModel: initializes AceStepHandler (DiT) and LLMHandler, parses Options.
|
||||
- SoundGeneration: uses create_sample (simple mode), format_sample (optional), then
|
||||
generate_music from acestep.inference. Writes first output to request.dst.
|
||||
- Fail hard: no fallback WAV on error; exceptions propagate to gRPC.
|
||||
"""
|
||||
from concurrent import futures
|
||||
import argparse
|
||||
import shutil
|
||||
import signal
|
||||
import sys
|
||||
import os
|
||||
import tempfile
|
||||
|
||||
import backend_pb2
|
||||
import backend_pb2_grpc
|
||||
import grpc
|
||||
from acestep.inference import (
|
||||
GenerationParams,
|
||||
GenerationConfig,
|
||||
generate_music,
|
||||
create_sample,
|
||||
format_sample,
|
||||
)
|
||||
from acestep.handler import AceStepHandler
|
||||
from acestep.llm_inference import LLMHandler
|
||||
from acestep.model_downloader import ensure_lm_model
|
||||
|
||||
|
||||
_ONE_DAY_IN_SECONDS = 60 * 60 * 24
|
||||
MAX_WORKERS = int(os.environ.get("PYTHON_GRPC_MAX_WORKERS", "1"))
|
||||
|
||||
# Model name -> HuggingFace/ModelScope repo (from upstream api_server.py)
|
||||
MODEL_REPO_MAPPING = {
|
||||
"acestep-v15-turbo": "ACE-Step/Ace-Step1.5",
|
||||
"acestep-5Hz-lm-0.6B": "ACE-Step/Ace-Step1.5",
|
||||
"acestep-5Hz-lm-1.7B": "ACE-Step/Ace-Step1.5",
|
||||
"vae": "ACE-Step/Ace-Step1.5",
|
||||
"Qwen3-Embedding-0.6B": "ACE-Step/Ace-Step1.5",
|
||||
"acestep-v15-base": "ACE-Step/acestep-v15-base",
|
||||
"acestep-v15-sft": "ACE-Step/acestep-v15-sft",
|
||||
"acestep-v15-turbo-shift3": "ACE-Step/acestep-v15-turbo-shift3",
|
||||
"acestep-5Hz-lm-4B": "ACE-Step/acestep-5Hz-lm-4B",
|
||||
}
|
||||
DEFAULT_REPO_ID = "ACE-Step/Ace-Step1.5"
|
||||
|
||||
def _is_float(s):
|
||||
try:
|
||||
float(s)
|
||||
return True
|
||||
except (ValueError, TypeError):
|
||||
return False
|
||||
|
||||
|
||||
def _is_int(s):
|
||||
try:
|
||||
int(s)
|
||||
return True
|
||||
except (ValueError, TypeError):
|
||||
return False
|
||||
|
||||
|
||||
def _parse_timesteps(s):
|
||||
if s is None or (isinstance(s, str) and not s.strip()):
|
||||
return None
|
||||
if isinstance(s, (list, tuple)):
|
||||
return [float(x) for x in s]
|
||||
try:
|
||||
return [float(x.strip()) for x in str(s).split(",") if x.strip()]
|
||||
except (ValueError, TypeError):
|
||||
return None
|
||||
|
||||
|
||||
def _parse_options(opts_list):
|
||||
"""Parse repeated 'key:value' options into a dict. Coerce numeric and bool."""
|
||||
out = {}
|
||||
for opt in opts_list or []:
|
||||
if ":" not in opt:
|
||||
continue
|
||||
key, value = opt.split(":", 1)
|
||||
key = key.strip()
|
||||
value = value.strip()
|
||||
if _is_int(value):
|
||||
out[key] = int(value)
|
||||
elif _is_float(value):
|
||||
out[key] = float(value)
|
||||
elif value.lower() in ("true", "false"):
|
||||
out[key] = value.lower() == "true"
|
||||
else:
|
||||
out[key] = value
|
||||
return out
|
||||
|
||||
|
||||
def _generate_audio_sync(servicer, payload, dst_path):
|
||||
"""
|
||||
Run full ACE-Step pipeline using acestep.inference:
|
||||
- If sample_mode/sample_query: create_sample() for caption/lyrics/metadata.
|
||||
- If use_format and caption/lyrics: format_sample().
|
||||
- Build GenerationParams and GenerationConfig, then generate_music().
|
||||
Writes the first generated audio to dst_path. Raises on failure.
|
||||
"""
|
||||
|
||||
opts = servicer.options
|
||||
dit_handler = servicer.dit_handler
|
||||
llm_handler = servicer.llm_handler
|
||||
|
||||
for key, value in opts.items():
|
||||
if key not in payload:
|
||||
payload[key] = value
|
||||
|
||||
def _opt(name, default):
|
||||
return opts.get(name, default)
|
||||
|
||||
lm_temperature = _opt("temperature", 0.85)
|
||||
lm_cfg_scale = _opt("lm_cfg_scale", _opt("cfg_scale", 2.0))
|
||||
lm_top_k = opts.get("top_k")
|
||||
lm_top_p = _opt("top_p", 0.9)
|
||||
if lm_top_p is not None and lm_top_p >= 1.0:
|
||||
lm_top_p = None
|
||||
inference_steps = _opt("inference_steps", 8)
|
||||
guidance_scale = _opt("guidance_scale", 7.0)
|
||||
batch_size = max(1, int(_opt("batch_size", 1)))
|
||||
|
||||
use_simple = bool(payload.get("sample_query") or payload.get("text"))
|
||||
sample_mode = use_simple and (payload.get("thinking") or payload.get("sample_mode"))
|
||||
sample_query = (payload.get("sample_query") or payload.get("text") or "").strip()
|
||||
use_format = bool(payload.get("use_format"))
|
||||
caption = (payload.get("prompt") or payload.get("caption") or "").strip()
|
||||
lyrics = (payload.get("lyrics") or "").strip()
|
||||
vocal_language = (payload.get("vocal_language") or "en").strip()
|
||||
instrumental = bool(payload.get("instrumental"))
|
||||
bpm = payload.get("bpm")
|
||||
key_scale = (payload.get("key_scale") or "").strip()
|
||||
time_signature = (payload.get("time_signature") or "").strip()
|
||||
audio_duration = payload.get("audio_duration")
|
||||
if audio_duration is not None:
|
||||
try:
|
||||
audio_duration = float(audio_duration)
|
||||
except (TypeError, ValueError):
|
||||
audio_duration = None
|
||||
|
||||
if sample_mode and llm_handler and getattr(llm_handler, "llm_initialized", False):
|
||||
parsed_language = None
|
||||
if sample_query:
|
||||
for hint in ("english", "en", "chinese", "zh", "japanese", "ja"):
|
||||
if hint in sample_query.lower():
|
||||
parsed_language = "en" if hint == "english" or hint == "en" else hint
|
||||
break
|
||||
vocal_lang = vocal_language if vocal_language and vocal_language != "unknown" else parsed_language
|
||||
sample_result = create_sample(
|
||||
llm_handler=llm_handler,
|
||||
query=sample_query or "NO USER INPUT",
|
||||
instrumental=instrumental,
|
||||
vocal_language=vocal_lang,
|
||||
temperature=lm_temperature,
|
||||
top_k=lm_top_k,
|
||||
top_p=lm_top_p,
|
||||
use_constrained_decoding=True,
|
||||
)
|
||||
if not sample_result.success:
|
||||
raise RuntimeError(f"create_sample failed: {sample_result.error or sample_result.status_message}")
|
||||
caption = sample_result.caption or caption
|
||||
lyrics = sample_result.lyrics or lyrics
|
||||
bpm = sample_result.bpm
|
||||
key_scale = sample_result.keyscale or key_scale
|
||||
time_signature = sample_result.timesignature or time_signature
|
||||
if sample_result.duration is not None:
|
||||
audio_duration = sample_result.duration
|
||||
if getattr(sample_result, "language", None):
|
||||
vocal_language = sample_result.language
|
||||
|
||||
if use_format and (caption or lyrics) and llm_handler and getattr(llm_handler, "llm_initialized", False):
|
||||
user_metadata = {}
|
||||
if bpm is not None:
|
||||
user_metadata["bpm"] = bpm
|
||||
if audio_duration is not None and float(audio_duration) > 0:
|
||||
user_metadata["duration"] = int(audio_duration)
|
||||
if key_scale:
|
||||
user_metadata["keyscale"] = key_scale
|
||||
if time_signature:
|
||||
user_metadata["timesignature"] = time_signature
|
||||
if vocal_language and vocal_language != "unknown":
|
||||
user_metadata["language"] = vocal_language
|
||||
format_result = format_sample(
|
||||
llm_handler=llm_handler,
|
||||
caption=caption,
|
||||
lyrics=lyrics,
|
||||
user_metadata=user_metadata if user_metadata else None,
|
||||
temperature=lm_temperature,
|
||||
top_k=lm_top_k,
|
||||
top_p=lm_top_p,
|
||||
use_constrained_decoding=True,
|
||||
)
|
||||
if format_result.success:
|
||||
caption = format_result.caption or caption
|
||||
lyrics = format_result.lyrics or lyrics
|
||||
if format_result.duration is not None:
|
||||
audio_duration = format_result.duration
|
||||
if format_result.bpm is not None:
|
||||
bpm = format_result.bpm
|
||||
if format_result.keyscale:
|
||||
key_scale = format_result.keyscale
|
||||
if format_result.timesignature:
|
||||
time_signature = format_result.timesignature
|
||||
if getattr(format_result, "language", None):
|
||||
vocal_language = format_result.language
|
||||
|
||||
thinking = bool(payload.get("thinking"))
|
||||
use_cot_metas = not sample_mode
|
||||
params = GenerationParams(
|
||||
task_type=payload.get("task_type", "text2music"),
|
||||
instruction=payload.get("instruction", "Fill the audio semantic mask based on the given conditions:"),
|
||||
reference_audio=payload.get("reference_audio_path"),
|
||||
src_audio=payload.get("src_audio_path"),
|
||||
audio_codes=payload.get("audio_code_string", ""),
|
||||
caption=caption,
|
||||
lyrics=lyrics,
|
||||
instrumental=instrumental or (not lyrics or str(lyrics).strip().lower() in ("[inst]", "[instrumental]")),
|
||||
vocal_language=vocal_language or "unknown",
|
||||
bpm=bpm,
|
||||
keyscale=key_scale,
|
||||
timesignature=time_signature,
|
||||
duration=float(audio_duration) if audio_duration and float(audio_duration) > 0 else -1.0,
|
||||
inference_steps=inference_steps,
|
||||
seed=int(payload.get("seed", -1)),
|
||||
guidance_scale=guidance_scale,
|
||||
use_adg=bool(payload.get("use_adg")),
|
||||
cfg_interval_start=float(payload.get("cfg_interval_start", 0.0)),
|
||||
cfg_interval_end=float(payload.get("cfg_interval_end", 1.0)),
|
||||
shift=float(payload.get("shift", 1.0)),
|
||||
infer_method=(payload.get("infer_method") or "ode").strip(),
|
||||
timesteps=_parse_timesteps(payload.get("timesteps")),
|
||||
repainting_start=float(payload.get("repainting_start", 0.0)),
|
||||
repainting_end=float(payload.get("repainting_end", -1)) if payload.get("repainting_end") is not None else -1,
|
||||
audio_cover_strength=float(payload.get("audio_cover_strength", 1.0)),
|
||||
thinking=thinking,
|
||||
lm_temperature=lm_temperature,
|
||||
lm_cfg_scale=lm_cfg_scale,
|
||||
lm_top_k=lm_top_k or 0,
|
||||
lm_top_p=lm_top_p if lm_top_p is not None and lm_top_p < 1.0 else 0.9,
|
||||
lm_negative_prompt=payload.get("lm_negative_prompt", "NO USER INPUT"),
|
||||
use_cot_metas=use_cot_metas,
|
||||
use_cot_caption=bool(payload.get("use_cot_caption", True)),
|
||||
use_cot_language=bool(payload.get("use_cot_language", True)),
|
||||
use_constrained_decoding=True,
|
||||
)
|
||||
|
||||
config = GenerationConfig(
|
||||
batch_size=batch_size,
|
||||
allow_lm_batch=bool(payload.get("allow_lm_batch", False)),
|
||||
use_random_seed=bool(payload.get("use_random_seed", True)),
|
||||
seeds=payload.get("seeds"),
|
||||
lm_batch_chunk_size=max(1, int(payload.get("lm_batch_chunk_size", 8))),
|
||||
constrained_decoding_debug=bool(payload.get("constrained_decoding_debug")),
|
||||
audio_format=(payload.get("audio_format") or "flac").strip() or "flac",
|
||||
)
|
||||
|
||||
save_dir = tempfile.mkdtemp(prefix="ace_step_")
|
||||
try:
|
||||
result = generate_music(
|
||||
dit_handler=dit_handler,
|
||||
llm_handler=llm_handler if (llm_handler and getattr(llm_handler, "llm_initialized", False)) else None,
|
||||
params=params,
|
||||
config=config,
|
||||
save_dir=save_dir,
|
||||
progress=None,
|
||||
)
|
||||
if not result.success:
|
||||
raise RuntimeError(result.error or result.status_message or "generate_music failed")
|
||||
|
||||
audios = result.audios or []
|
||||
if not audios:
|
||||
raise RuntimeError("generate_music returned no audio")
|
||||
|
||||
first_path = audios[0].get("path") or ""
|
||||
if not first_path or not os.path.isfile(first_path):
|
||||
raise RuntimeError("first generated audio path missing or not a file")
|
||||
|
||||
shutil.copy2(first_path, dst_path)
|
||||
finally:
|
||||
try:
|
||||
shutil.rmtree(save_dir, ignore_errors=True)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
class BackendServicer(backend_pb2_grpc.BackendServicer):
|
||||
def __init__(self):
|
||||
self.model_path = None
|
||||
self.model_dir = None
|
||||
self.checkpoint_dir = None
|
||||
self.project_root = None
|
||||
self.options = {}
|
||||
self.dit_handler = None
|
||||
self.llm_handler = None
|
||||
|
||||
def Health(self, request, context):
|
||||
return backend_pb2.Reply(message=b"OK")
|
||||
|
||||
def LoadModel(self, request, context):
|
||||
try:
|
||||
self.options = _parse_options(list(getattr(request, "Options", []) or []))
|
||||
model_path = getattr(request, "ModelPath", None) or ""
|
||||
model_name = (request.Model or "").strip()
|
||||
model_file = (getattr(request, "ModelFile", None) or "").strip()
|
||||
|
||||
# Model dir: where we store checkpoints (always under LocalAI models path, never backend dir)
|
||||
if model_path and model_name:
|
||||
model_dir = os.path.join(model_path, model_name)
|
||||
elif model_file:
|
||||
model_dir = model_file
|
||||
else:
|
||||
model_dir = os.path.abspath(model_name or ".")
|
||||
self.model_dir = model_dir
|
||||
self.checkpoint_dir = os.path.join(model_dir, "checkpoints")
|
||||
self.project_root = model_dir
|
||||
self.model_path = os.path.join(self.checkpoint_dir, model_name or os.path.basename(model_dir.rstrip("/\\")))
|
||||
|
||||
config_path = model_name or os.path.basename(model_dir.rstrip("/\\"))
|
||||
os.makedirs(self.checkpoint_dir, exist_ok=True)
|
||||
|
||||
self.dit_handler = AceStepHandler()
|
||||
# Patch handler so it uses our model dir instead of site-packages/checkpoints
|
||||
self.dit_handler._get_project_root = lambda: self.project_root
|
||||
device = self.options.get("device", "auto")
|
||||
use_flash = self.options.get("use_flash_attention", True)
|
||||
if isinstance(use_flash, str):
|
||||
use_flash = str(use_flash).lower() in ("1", "true", "yes")
|
||||
offload = self.options.get("offload_to_cpu", False)
|
||||
if isinstance(offload, str):
|
||||
offload = str(offload).lower() in ("1", "true", "yes")
|
||||
status_msg, ok = self.dit_handler.initialize_service(
|
||||
project_root=self.project_root,
|
||||
config_path=config_path,
|
||||
device=device,
|
||||
use_flash_attention=use_flash,
|
||||
compile_model=False,
|
||||
offload_to_cpu=offload,
|
||||
offload_dit_to_cpu=bool(self.options.get("offload_dit_to_cpu", False)),
|
||||
)
|
||||
if not ok:
|
||||
return backend_pb2.Result(success=False, message=f"DiT init failed: {status_msg}")
|
||||
|
||||
self.llm_handler = None
|
||||
if self.options.get("init_lm", True):
|
||||
lm_model = self.options.get("lm_model_path", "acestep-5Hz-lm-0.6B")
|
||||
|
||||
# Ensure LM model is downloaded before initializing
|
||||
try:
|
||||
from pathlib import Path
|
||||
lm_success, lm_msg = ensure_lm_model(
|
||||
model_name=lm_model,
|
||||
checkpoints_dir=Path(self.checkpoint_dir),
|
||||
prefer_source=None, # Auto-detect HuggingFace vs ModelScope
|
||||
)
|
||||
if not lm_success:
|
||||
print(f"[ace-step] Warning: LM model download failed: {lm_msg}", file=sys.stderr)
|
||||
# Continue anyway - LLM initialization will fail gracefully
|
||||
else:
|
||||
print(f"[ace-step] LM model ready: {lm_msg}", file=sys.stderr)
|
||||
except Exception as e:
|
||||
print(f"[ace-step] Warning: LM model download check failed: {e}", file=sys.stderr)
|
||||
# Continue anyway - LLM initialization will fail gracefully
|
||||
|
||||
self.llm_handler = LLMHandler()
|
||||
lm_backend = (self.options.get("lm_backend") or "vllm").strip().lower()
|
||||
if lm_backend not in ("vllm", "pt"):
|
||||
lm_backend = "vllm"
|
||||
lm_status, lm_ok = self.llm_handler.initialize(
|
||||
checkpoint_dir=self.checkpoint_dir,
|
||||
lm_model_path=lm_model,
|
||||
backend=lm_backend,
|
||||
device=device,
|
||||
offload_to_cpu=offload,
|
||||
dtype=getattr(self.dit_handler, "dtype", None),
|
||||
)
|
||||
if not lm_ok:
|
||||
self.llm_handler = None
|
||||
print(f"[ace-step] LM init failed (optional): {lm_status}", file=sys.stderr)
|
||||
|
||||
print(f"[ace-step] LoadModel: model={self.model_path}, options={list(self.options.keys())}", file=sys.stderr)
|
||||
return backend_pb2.Result(success=True, message="Model loaded successfully")
|
||||
except Exception as err:
|
||||
return backend_pb2.Result(success=False, message=f"LoadModel error: {err}")
|
||||
|
||||
def SoundGeneration(self, request, context):
|
||||
if not request.dst:
|
||||
return backend_pb2.Result(success=False, message="request.dst is required")
|
||||
|
||||
use_simple = bool(request.text)
|
||||
if use_simple:
|
||||
payload = {
|
||||
"sample_query": request.text or "",
|
||||
"sample_mode": True,
|
||||
"thinking": True,
|
||||
"vocal_language": request.language or request.GetLanguage() or "en",
|
||||
"instrumental": request.instrumental if request.HasField("instrumental") else False,
|
||||
}
|
||||
else:
|
||||
caption = request.caption or request.GetCaption() or request.text
|
||||
payload = {
|
||||
"prompt": caption,
|
||||
"lyrics": request.lyrics or request.lyrics or "",
|
||||
"thinking": request.think if request.HasField("think") else False,
|
||||
"vocal_language": request.language or request.GetLanguage() or "en",
|
||||
}
|
||||
if request.HasField("bpm"):
|
||||
payload["bpm"] = request.bpm
|
||||
if request.HasField("keyscale") and request.keyscale:
|
||||
payload["key_scale"] = request.keyscale
|
||||
if request.HasField("timesignature") and request.timesignature:
|
||||
payload["time_signature"] = request.timesignature
|
||||
if request.HasField("duration") and request.duration:
|
||||
payload["audio_duration"] = int(request.duration) if request.duration else None
|
||||
if request.src:
|
||||
payload["src_audio_path"] = request.src
|
||||
|
||||
_generate_audio_sync(self, payload, request.dst)
|
||||
return backend_pb2.Result(success=True, message="Sound generated successfully")
|
||||
|
||||
def TTS(self, request, context):
|
||||
if not request.dst:
|
||||
return backend_pb2.Result(success=False, message="request.dst is required")
|
||||
payload = {
|
||||
"sample_query": request.text,
|
||||
"sample_mode": True,
|
||||
"thinking": False,
|
||||
"vocal_language": (request.language if request.language else "") or "en",
|
||||
"instrumental": False,
|
||||
}
|
||||
_generate_audio_sync(self, payload, request.dst)
|
||||
return backend_pb2.Result(success=True, message="TTS (music fallback) generated successfully")
|
||||
|
||||
|
||||
def serve(address):
|
||||
server = grpc.server(
|
||||
futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
|
||||
options=[
|
||||
("grpc.max_message_length", 50 * 1024 * 1024),
|
||||
("grpc.max_send_message_length", 50 * 1024 * 1024),
|
||||
("grpc.max_receive_message_length", 50 * 1024 * 1024),
|
||||
],
|
||||
)
|
||||
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
|
||||
server.add_insecure_port(address)
|
||||
server.start()
|
||||
print(f"[ace-step] Server listening on {address}", file=sys.stderr)
|
||||
|
||||
def shutdown(sig, frame):
|
||||
server.stop(0)
|
||||
sys.exit(0)
|
||||
|
||||
signal.signal(signal.SIGINT, shutdown)
|
||||
signal.signal(signal.SIGTERM, shutdown)
|
||||
|
||||
try:
|
||||
while True:
|
||||
import time
|
||||
time.sleep(_ONE_DAY_IN_SECONDS)
|
||||
except KeyboardInterrupt:
|
||||
server.stop(0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--addr", default="localhost:50051", help="Listen address")
|
||||
args = parser.parse_args()
|
||||
serve(args.addr)
|
||||
@@ -1,26 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
backend_dir=$(dirname $0)
|
||||
if [ -d $backend_dir/common ]; then
|
||||
source $backend_dir/common/libbackend.sh
|
||||
else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
PYTHON_VERSION="3.11"
|
||||
PYTHON_PATCH="14"
|
||||
PY_STANDALONE_TAG="20260203"
|
||||
|
||||
installRequirements
|
||||
|
||||
if [ ! -d ACE-Step-1.5 ]; then
|
||||
git clone https://github.com/ace-step/ACE-Step-1.5
|
||||
cd ACE-Step-1.5/
|
||||
if [ "x${USE_PIP}" == "xtrue" ]; then
|
||||
pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
|
||||
else
|
||||
uv pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
|
||||
fi
|
||||
fi
|
||||
|
||||
@@ -1,22 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/cpu
|
||||
torch
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
@@ -1,22 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/cu128
|
||||
torch
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio>=6.5.1
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
@@ -1,22 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/cu130
|
||||
torch
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio>=6.5.1
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
@@ -1,22 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/rocm6.4
|
||||
torch==2.8.0+rocm6.4
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio>=6.5.1
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
@@ -1,26 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/xpu
|
||||
torch
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
|
||||
# LoRA Training dependencies (optional)
|
||||
peft>=0.7.0
|
||||
lightning>=2.0.0
|
||||
@@ -1,21 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/cu130
|
||||
torch
|
||||
torchaudio
|
||||
torchvision
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio>=6.5.1
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
@@ -1,25 +0,0 @@
|
||||
torch
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
# Core dependencies
|
||||
transformers>=4.51.0,<4.58.0
|
||||
diffusers
|
||||
gradio
|
||||
matplotlib>=3.7.5
|
||||
scipy>=1.10.1
|
||||
soundfile>=0.13.1
|
||||
loguru>=0.7.3
|
||||
einops>=0.8.1
|
||||
accelerate>=1.12.0
|
||||
fastapi>=0.110.0
|
||||
uvicorn[standard]>=0.27.0
|
||||
numba>=0.63.1
|
||||
vector-quantize-pytorch>=1.27.15
|
||||
torchcodec>=0.9.1
|
||||
torchao
|
||||
modelscope
|
||||
|
||||
# LoRA Training dependencies (optional)
|
||||
peft>=0.7.0
|
||||
lightning>=2.0.0
|
||||
@@ -1,4 +0,0 @@
|
||||
setuptools
|
||||
grpcio==1.76.0
|
||||
protobuf
|
||||
certifi
|
||||
@@ -1,9 +0,0 @@
|
||||
#!/bin/bash
|
||||
backend_dir=$(dirname $0)
|
||||
if [ -d $backend_dir/common ]; then
|
||||
source $backend_dir/common/libbackend.sh
|
||||
else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
startBackend $@
|
||||
@@ -1,53 +0,0 @@
|
||||
"""
|
||||
Tests for the ACE-Step gRPC backend.
|
||||
"""
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
import backend_pb2
|
||||
import backend_pb2_grpc
|
||||
import grpc
|
||||
|
||||
|
||||
class TestACEStepBackend(unittest.TestCase):
|
||||
"""Test Health, LoadModel, and SoundGeneration (minimal; no real model required)."""
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
port = os.environ.get("BACKEND_PORT", "50051")
|
||||
cls.channel = grpc.insecure_channel(f"localhost:{port}")
|
||||
cls.stub = backend_pb2_grpc.BackendStub(cls.channel)
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
cls.channel.close()
|
||||
|
||||
def test_health(self):
|
||||
response = self.stub.Health(backend_pb2.HealthMessage())
|
||||
self.assertEqual(response.message, b"OK")
|
||||
|
||||
def test_load_model(self):
|
||||
response = self.stub.LoadModel(backend_pb2.ModelOptions(Model="ace-step-test"))
|
||||
self.assertTrue(response.success, response.message)
|
||||
|
||||
def test_sound_generation_minimal(self):
|
||||
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
|
||||
dst = f.name
|
||||
try:
|
||||
req = backend_pb2.SoundGenerationRequest(
|
||||
text="upbeat pop song",
|
||||
model="ace-step-test",
|
||||
dst=dst,
|
||||
)
|
||||
response = self.stub.SoundGeneration(req)
|
||||
self.assertTrue(response.success, response.message)
|
||||
self.assertTrue(os.path.exists(dst), f"Output file not created: {dst}")
|
||||
self.assertGreater(os.path.getsize(dst), 0)
|
||||
finally:
|
||||
if os.path.exists(dst):
|
||||
os.unlink(dst)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,19 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
backend_dir=$(dirname $0)
|
||||
if [ -d $backend_dir/common ]; then
|
||||
source $backend_dir/common/libbackend.sh
|
||||
else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
# Start backend in background (use env to avoid port conflict in parallel tests)
|
||||
export PYTHONUNBUFFERED=1
|
||||
BACKEND_PORT=${BACKEND_PORT:-50051}
|
||||
python backend.py --addr "localhost:${BACKEND_PORT}" &
|
||||
BACKEND_PID=$!
|
||||
trap "kill $BACKEND_PID 2>/dev/null || true" EXIT
|
||||
sleep 3
|
||||
export BACKEND_PORT
|
||||
runUnittests
|
||||
@@ -1,7 +0,0 @@
|
||||
torch
|
||||
torchaudio
|
||||
accelerate
|
||||
numpy>=1.24.0,<1.26.0
|
||||
transformers
|
||||
# https://github.com/mudler/LocalAI/pull/6240#issuecomment-3329518289
|
||||
chatterbox-tts@git+https://git@github.com/mudler/chatterbox.git@faster
|
||||
@@ -1,4 +0,0 @@
|
||||
torch==2.7.1
|
||||
transformers==4.48.3
|
||||
accelerate
|
||||
coqui-tts
|
||||
@@ -1,8 +0,0 @@
|
||||
torch==2.7.1
|
||||
faster-whisper
|
||||
opencv-python
|
||||
accelerate
|
||||
compel
|
||||
peft
|
||||
sentencepiece
|
||||
optimum-quanto
|
||||
@@ -1,5 +0,0 @@
|
||||
grpcio==1.71.0
|
||||
protobuf
|
||||
certifi
|
||||
packaging==24.1
|
||||
https://github.com/KittenML/KittenTTS/releases/download/0.1/kittentts-0.1.0-py3-none-any.whl
|
||||
@@ -1,5 +0,0 @@
|
||||
torch==2.7.1
|
||||
transformers
|
||||
accelerate
|
||||
kokoro
|
||||
soundfile
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-audio
|
||||
mlx[cpu]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-audio
|
||||
mlx[cuda12]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-audio
|
||||
mlx[cuda13]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-audio
|
||||
mlx[cuda12]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-audio
|
||||
mlx[cuda13]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-vlm
|
||||
mlx[cpu]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-vlm
|
||||
mlx[cuda12]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-vlm
|
||||
mlx[cuda13]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-vlm
|
||||
mlx[cuda12]
|
||||
@@ -1,2 +0,0 @@
|
||||
git+https://github.com/Blaizzy/mlx-vlm
|
||||
mlx[cuda13]
|
||||
@@ -1,2 +0,0 @@
|
||||
mlx-lm
|
||||
mlx[cpu]
|
||||
@@ -1,2 +0,0 @@
|
||||
mlx-lm
|
||||
mlx[cuda12]
|
||||
@@ -1,2 +0,0 @@
|
||||
mlx-lm
|
||||
mlx[cuda13]
|
||||
@@ -1,2 +0,0 @@
|
||||
mlx-lm
|
||||
mlx[cuda12]
|
||||
@@ -1,2 +0,0 @@
|
||||
mlx-lm
|
||||
mlx[cuda13]
|
||||
@@ -1,4 +0,0 @@
|
||||
grpcio==1.71.0
|
||||
protobuf
|
||||
grpcio-tools
|
||||
useful-moonshine-onnx@git+https://git@github.com/moonshine-ai/moonshine.git#subdirectory=moonshine-onnx
|
||||
@@ -1,23 +0,0 @@
|
||||
.PHONY: outetts
|
||||
outetts:
|
||||
bash install.sh
|
||||
|
||||
.PHONY: run
|
||||
run: outetts
|
||||
@echo "Running outetts..."
|
||||
bash run.sh
|
||||
@echo "outetts run."
|
||||
|
||||
.PHONY: test
|
||||
test: outetts
|
||||
@echo "Testing outetts..."
|
||||
bash test.sh
|
||||
@echo "outetts tested."
|
||||
|
||||
.PHONY: protogen-clean
|
||||
protogen-clean:
|
||||
$(RM) backend_pb2_grpc.py backend_pb2.py
|
||||
|
||||
.PHONY: clean
|
||||
clean: protogen-clean
|
||||
rm -rf venv __pycache__
|
||||
@@ -1,138 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
gRPC server for OuteTTS (OuteAI TTS) models.
|
||||
"""
|
||||
from concurrent import futures
|
||||
|
||||
import argparse
|
||||
import signal
|
||||
import sys
|
||||
import os
|
||||
import asyncio
|
||||
|
||||
import backend_pb2
|
||||
import backend_pb2_grpc
|
||||
|
||||
import grpc
|
||||
import outetts
|
||||
|
||||
_ONE_DAY_IN_SECONDS = 60 * 60 * 24
|
||||
|
||||
MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
|
||||
|
||||
|
||||
class BackendServicer(backend_pb2_grpc.BackendServicer):
|
||||
def Health(self, request, context):
|
||||
return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
|
||||
|
||||
def LoadModel(self, request, context):
|
||||
model_name = request.Model
|
||||
if os.path.exists(request.ModelFile):
|
||||
model_name = request.ModelFile
|
||||
|
||||
self.options = {}
|
||||
for opt in request.Options:
|
||||
if ":" not in opt:
|
||||
continue
|
||||
key, value = opt.split(":", 1)
|
||||
try:
|
||||
if "." in value:
|
||||
value = float(value)
|
||||
else:
|
||||
value = int(value)
|
||||
except ValueError:
|
||||
pass
|
||||
self.options[key] = value
|
||||
|
||||
MODELNAME = "OuteAI/OuteTTS-0.3-1B"
|
||||
TOKENIZER = "OuteAI/OuteTTS-0.3-1B"
|
||||
VERSION = "0.3"
|
||||
SPEAKER = "en_male_1"
|
||||
for opt in request.Options:
|
||||
if opt.startswith("tokenizer:"):
|
||||
TOKENIZER = opt.split(":")[1]
|
||||
break
|
||||
if opt.startswith("version:"):
|
||||
VERSION = opt.split(":")[1]
|
||||
break
|
||||
if opt.startswith("speaker:"):
|
||||
SPEAKER = opt.split(":")[1]
|
||||
break
|
||||
|
||||
if model_name != "":
|
||||
MODELNAME = model_name
|
||||
|
||||
try:
|
||||
model_config = outetts.HFModelConfig_v2(
|
||||
model_path=MODELNAME,
|
||||
tokenizer_path=TOKENIZER
|
||||
)
|
||||
self.interface = outetts.InterfaceHF(model_version=VERSION, cfg=model_config)
|
||||
|
||||
self.interface.print_default_speakers()
|
||||
if request.AudioPath:
|
||||
if os.path.isabs(request.AudioPath):
|
||||
self.AudioPath = request.AudioPath
|
||||
else:
|
||||
self.AudioPath = os.path.join(request.ModelPath, request.AudioPath)
|
||||
self.speaker = self.interface.create_speaker(audio_path=self.AudioPath)
|
||||
else:
|
||||
self.speaker = self.interface.load_default_speaker(name=SPEAKER)
|
||||
|
||||
if request.ContextSize > 0:
|
||||
self.max_tokens = request.ContextSize
|
||||
else:
|
||||
self.max_tokens = self.options.get("max_new_tokens", 512)
|
||||
|
||||
except Exception as err:
|
||||
print("Error:", err, file=sys.stderr)
|
||||
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
|
||||
return backend_pb2.Result(message="Model loaded successfully", success=True)
|
||||
|
||||
def TTS(self, request, context):
|
||||
try:
|
||||
text = request.text if request.text else "Speech synthesis is the artificial production of human speech."
|
||||
print("[OuteTTS] generating TTS", file=sys.stderr)
|
||||
gen_cfg = outetts.GenerationConfig(
|
||||
text=text,
|
||||
temperature=self.options.get("temperature", 0.1),
|
||||
repetition_penalty=self.options.get("repetition_penalty", 1.1),
|
||||
max_length=self.max_tokens,
|
||||
speaker=self.speaker,
|
||||
)
|
||||
output = self.interface.generate(config=gen_cfg)
|
||||
print("[OuteTTS] Generated TTS", file=sys.stderr)
|
||||
output.save(request.dst)
|
||||
print("[OuteTTS] TTS done", file=sys.stderr)
|
||||
except Exception as err:
|
||||
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
|
||||
return backend_pb2.Result(success=True)
|
||||
|
||||
|
||||
async def serve(address):
|
||||
server = grpc.aio.server(
|
||||
migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
|
||||
options=[
|
||||
('grpc.max_message_length', 50 * 1024 * 1024),
|
||||
('grpc.max_send_message_length', 50 * 1024 * 1024),
|
||||
('grpc.max_receive_message_length', 50 * 1024 * 1024),
|
||||
])
|
||||
backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
|
||||
server.add_insecure_port(address)
|
||||
|
||||
loop = asyncio.get_event_loop()
|
||||
for sig in (signal.SIGINT, signal.SIGTERM):
|
||||
loop.add_signal_handler(
|
||||
sig, lambda: asyncio.ensure_future(server.stop(5))
|
||||
)
|
||||
|
||||
await server.start()
|
||||
print("Server started. Listening on: " + address, file=sys.stderr)
|
||||
await server.wait_for_termination()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Run the OuteTTS gRPC server.")
|
||||
parser.add_argument("--addr", default="localhost:50051", help="The address to bind the server to.")
|
||||
args = parser.parse_args()
|
||||
asyncio.run(serve(args.addr))
|
||||
@@ -1,11 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
backend_dir=$(dirname $0)
|
||||
if [ -d $backend_dir/common ]; then
|
||||
source $backend_dir/common/libbackend.sh
|
||||
else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
installRequirements
|
||||
@@ -1,7 +0,0 @@
|
||||
torch==2.7.1
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
accelerate
|
||||
bitsandbytes
|
||||
outetts
|
||||
protobuf==6.33.5
|
||||
@@ -1,7 +0,0 @@
|
||||
torch==2.7.1
|
||||
accelerate
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
bitsandbytes
|
||||
protobuf==6.33.5
|
||||
outetts
|
||||
@@ -1,7 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/cu130
|
||||
torch==2.9.0
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
bitsandbytes
|
||||
outetts
|
||||
protobuf==6.33.5
|
||||
@@ -1,8 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/rocm6.4
|
||||
torch==2.8.0+rocm6.4
|
||||
accelerate
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
bitsandbytes
|
||||
outetts
|
||||
protobuf==6.33.5
|
||||
@@ -1,8 +0,0 @@
|
||||
--extra-index-url https://download.pytorch.org/whl/xpu
|
||||
torch
|
||||
optimum[openvino]
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
bitsandbytes
|
||||
outetts
|
||||
protobuf==6.33.5
|
||||
@@ -1,6 +0,0 @@
|
||||
grpcio==1.76.0
|
||||
protobuf==6.33.5
|
||||
certifi
|
||||
setuptools
|
||||
scipy==1.15.1
|
||||
numpy>=2.0.0
|
||||
@@ -1,9 +0,0 @@
|
||||
#!/bin/bash
|
||||
backend_dir=$(dirname $0)
|
||||
if [ -d $backend_dir/common ]; then
|
||||
source $backend_dir/common/libbackend.sh
|
||||
else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
startBackend $@
|
||||
@@ -1,35 +0,0 @@
|
||||
"""
|
||||
Test script for the OuteTTS gRPC service.
|
||||
"""
|
||||
import unittest
|
||||
import subprocess
|
||||
import time
|
||||
import backend_pb2
|
||||
import backend_pb2_grpc
|
||||
|
||||
import grpc
|
||||
|
||||
|
||||
class TestBackendServicer(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.service = subprocess.Popen(["python3", "backend.py", "--addr", "localhost:50051"])
|
||||
time.sleep(5)
|
||||
|
||||
def tearDown(self):
|
||||
self.service.terminate()
|
||||
self.service.wait()
|
||||
|
||||
def test_health(self):
|
||||
try:
|
||||
with grpc.insecure_channel("localhost:50051") as channel:
|
||||
stub = backend_pb2_grpc.BackendStub(channel)
|
||||
response = stub.Health(backend_pb2.HealthMessage())
|
||||
self.assertEqual(response.message, b'OK')
|
||||
except Exception as err:
|
||||
self.fail(f"Health check failed: {err}")
|
||||
finally:
|
||||
self.tearDown()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,11 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
backend_dir=$(dirname $0)
|
||||
if [ -d $backend_dir/common ]; then
|
||||
source $backend_dir/common/libbackend.sh
|
||||
else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
runUnittests
|
||||
@@ -1,3 +1,5 @@
|
||||
.DEFAULT_GOAL := install
|
||||
|
||||
.PHONY: qwen-asr
|
||||
qwen-asr:
|
||||
bash install.sh
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
torch
|
||||
torchaudio
|
||||
torch==2.7.1
|
||||
torchaudio==0.22.1
|
||||
qwen-tts
|
||||
sox
|
||||
@@ -4,4 +4,3 @@ certifi
|
||||
packaging==24.1
|
||||
soundfile
|
||||
setuptools
|
||||
six
|
||||
@@ -28,7 +28,7 @@ class TestBackendServicer(unittest.TestCase):
|
||||
stderr=subprocess.PIPE,
|
||||
text=True
|
||||
)
|
||||
time.sleep(30)
|
||||
time.sleep(5)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
"""
|
||||
|
||||
@@ -1,4 +0,0 @@
|
||||
torch==2.7.1
|
||||
transformers
|
||||
accelerate
|
||||
rerankers[transformers]
|
||||
@@ -1,7 +0,0 @@
|
||||
torch==2.7.1
|
||||
rfdetr
|
||||
opencv-python
|
||||
accelerate
|
||||
peft
|
||||
inference
|
||||
optimum-quanto
|
||||
@@ -24,6 +24,7 @@ XPU=os.environ.get("XPU", "0") == "1"
|
||||
from transformers import AutoTokenizer, AutoModel, set_seed, TextIteratorStreamer, StoppingCriteriaList, StopStringCriteria, MambaConfig, MambaForCausalLM
|
||||
from transformers import AutoProcessor, MusicgenForConditionalGeneration, DiaForConditionalGeneration
|
||||
from scipy.io import wavfile
|
||||
import outetts
|
||||
from sentence_transformers import SentenceTransformer
|
||||
|
||||
|
||||
@@ -88,6 +89,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
|
||||
|
||||
self.CUDA = torch.cuda.is_available()
|
||||
self.OV=False
|
||||
self.OuteTTS=False
|
||||
self.DiaTTS=False
|
||||
self.SentenceTransformer = False
|
||||
|
||||
@@ -237,6 +239,45 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
|
||||
self.processor = self.processor.to("cuda")
|
||||
print("DiaForConditionalGeneration loaded", file=sys.stderr)
|
||||
self.DiaTTS = True
|
||||
elif request.Type == "OuteTTS":
|
||||
autoTokenizer = False
|
||||
options = request.Options
|
||||
MODELNAME = "OuteAI/OuteTTS-0.3-1B"
|
||||
TOKENIZER = "OuteAI/OuteTTS-0.3-1B"
|
||||
VERSION = "0.3"
|
||||
SPEAKER = "en_male_1"
|
||||
for opt in options:
|
||||
if opt.startswith("tokenizer:"):
|
||||
TOKENIZER = opt.split(":")[1]
|
||||
break
|
||||
if opt.startswith("version:"):
|
||||
VERSION = opt.split(":")[1]
|
||||
break
|
||||
if opt.startswith("speaker:"):
|
||||
SPEAKER = opt.split(":")[1]
|
||||
break
|
||||
|
||||
if model_name != "":
|
||||
MODELNAME = model_name
|
||||
|
||||
# Configure the model
|
||||
model_config = outetts.HFModelConfig_v2(
|
||||
model_path=MODELNAME,
|
||||
tokenizer_path=TOKENIZER
|
||||
)
|
||||
# Initialize the interface
|
||||
self.interface = outetts.InterfaceHF(model_version=VERSION, cfg=model_config)
|
||||
self.OuteTTS = True
|
||||
|
||||
self.interface.print_default_speakers()
|
||||
if request.AudioPath:
|
||||
if os.path.isabs(request.AudioPath):
|
||||
self.AudioPath = request.AudioPath
|
||||
else:
|
||||
self.AudioPath = os.path.join(request.ModelPath, request.AudioPath)
|
||||
self.speaker = self.interface.create_speaker(audio_path=self.AudioPath)
|
||||
else:
|
||||
self.speaker = self.interface.load_default_speaker(name=SPEAKER)
|
||||
elif request.Type == "SentenceTransformer":
|
||||
autoTokenizer = False
|
||||
self.model = SentenceTransformer(model_name, trust_remote_code=request.TrustRemoteCode)
|
||||
@@ -547,8 +588,30 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
|
||||
return backend_pb2.Result(success=True)
|
||||
|
||||
|
||||
def CallOuteTTS(self, request, context):
|
||||
try:
|
||||
print("[OuteTTS] generating TTS", file=sys.stderr)
|
||||
gen_cfg = outetts.GenerationConfig(
|
||||
text="Speech synthesis is the artificial production of human speech.",
|
||||
temperature=self.options.get("temperature", 0.1),
|
||||
repetition_penalty=self.options.get("repetition_penalty", 1.1),
|
||||
max_length=self.max_tokens,
|
||||
speaker=self.speaker,
|
||||
# voice_characteristics="upbeat enthusiasm, friendliness, clarity, professionalism, and trustworthiness"
|
||||
)
|
||||
output = self.interface.generate(config=gen_cfg)
|
||||
print("[OuteTTS] Generated TTS", file=sys.stderr)
|
||||
output.save(request.dst)
|
||||
print("[OuteTTS] TTS done", file=sys.stderr)
|
||||
except Exception as err:
|
||||
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
|
||||
return backend_pb2.Result(success=True)
|
||||
|
||||
# The TTS endpoint is older, and provides fewer features, but exists for compatibility reasons
|
||||
def TTS(self, request, context):
|
||||
if self.OuteTTS:
|
||||
return self.CallOuteTTS(request, context)
|
||||
|
||||
if self.DiaTTS:
|
||||
print("DiaTTS", file=sys.stderr)
|
||||
return self.CallDiaTTS(request, context)
|
||||
|
||||
@@ -4,5 +4,6 @@ numba==0.60.0
|
||||
accelerate
|
||||
transformers
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
outetts
|
||||
sentence-transformers==5.2.0
|
||||
protobuf==6.33.4
|
||||
@@ -4,5 +4,6 @@ llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
transformers
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
outetts
|
||||
sentence-transformers==5.2.0
|
||||
protobuf==6.33.4
|
||||
@@ -4,5 +4,6 @@ llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
transformers
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
outetts
|
||||
sentence-transformers==5.2.0
|
||||
protobuf==6.33.4
|
||||
@@ -5,5 +5,7 @@ transformers
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
outetts
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.0
|
||||
protobuf==6.33.4
|
||||
@@ -5,5 +5,6 @@ llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
transformers
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
outetts
|
||||
sentence-transformers==5.2.0
|
||||
protobuf==6.33.4
|
||||
@@ -1,8 +0,0 @@
|
||||
torch==2.7.1
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
accelerate
|
||||
transformers
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
@@ -1,5 +1,5 @@
|
||||
grpcio==1.76.0
|
||||
protobuf==6.33.5
|
||||
protobuf==6.33.4
|
||||
certifi
|
||||
setuptools
|
||||
scipy==1.15.1
|
||||
|
||||
@@ -21,9 +21,9 @@ if [ -n "$VOXCPM_PATH" ] && [ -f "$VOXCPM_PATH/modules/minicpm4/model.py" ]; the
|
||||
echo "Applying patch to voxcpm at $VOXCPM_PATH/modules/minicpm4/model.py"
|
||||
# Replace .contiguous() with .unsqueeze(0) for the three lines in the attention forward_step method
|
||||
# This fixes the dimension error in scaled_dot_product_attention
|
||||
# Use temp file for in-place edit so it works on both BSD sed (macOS) and GNU sed (Linux)
|
||||
PATCH_FILE="$VOXCPM_PATH/modules/minicpm4/model.py"
|
||||
sed 's/query_states = query_states\.contiguous()/query_states = query_states.unsqueeze(0)/g; s/key_cache = key_cache\.contiguous()/key_cache = key_cache.unsqueeze(0)/g; s/value_cache = value_cache\.contiguous()/value_cache = value_cache.unsqueeze(0)/g' "$PATCH_FILE" > "${PATCH_FILE}.tmp" && mv "${PATCH_FILE}.tmp" "$PATCH_FILE"
|
||||
sed -i 's/query_states = query_states\.contiguous()/query_states = query_states.unsqueeze(0)/g' "$VOXCPM_PATH/modules/minicpm4/model.py"
|
||||
sed -i 's/key_cache = key_cache\.contiguous()/key_cache = key_cache.unsqueeze(0)/g' "$VOXCPM_PATH/modules/minicpm4/model.py"
|
||||
sed -i 's/value_cache = value_cache\.contiguous()/value_cache = value_cache.unsqueeze(0)/g' "$VOXCPM_PATH/modules/minicpm4/model.py"
|
||||
echo "Patch applied successfully"
|
||||
else
|
||||
echo "Warning: Could not find voxcpm installation to apply patch (path: ${VOXCPM_PATH:-not found})"
|
||||
|
||||
@@ -8,8 +8,6 @@ else
|
||||
source $backend_dir/../common/libbackend.sh
|
||||
fi
|
||||
|
||||
if [ "x${BUILD_PROFILE}" != "xmetal" ] && [ "x${BUILD_PROFILE}" != "xmps" ]; then
|
||||
EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy unsafe-best-match"
|
||||
fi
|
||||
EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy unsafe-best-match"
|
||||
|
||||
installRequirements
|
||||
|
||||
@@ -1,2 +0,0 @@
|
||||
torch
|
||||
whisperx @ git+https://github.com/m-bain/whisperX.git
|
||||
@@ -19,14 +19,6 @@ func SoundGeneration(
|
||||
doSample *bool,
|
||||
sourceFile *string,
|
||||
sourceDivisor *int32,
|
||||
think *bool,
|
||||
caption string,
|
||||
lyrics string,
|
||||
bpm *int32,
|
||||
keyscale string,
|
||||
language string,
|
||||
timesignature string,
|
||||
instrumental *bool,
|
||||
loader *model.ModelLoader,
|
||||
appConfig *config.ApplicationConfig,
|
||||
modelConfig config.ModelConfig,
|
||||
@@ -53,11 +45,8 @@ func SoundGeneration(
|
||||
|
||||
fileName := utils.GenerateUniqueFileName(audioDir, "sound_generation", ".wav")
|
||||
filePath := filepath.Join(audioDir, fileName)
|
||||
if filePath, err = filepath.Abs(filePath); err != nil {
|
||||
return "", nil, fmt.Errorf("failed resolving sound generation path: %w", err)
|
||||
}
|
||||
|
||||
req := &proto.SoundGenerationRequest{
|
||||
res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
|
||||
Text: text,
|
||||
Model: modelConfig.Model,
|
||||
Dst: filePath,
|
||||
@@ -66,38 +55,12 @@ func SoundGeneration(
|
||||
Temperature: temperature,
|
||||
Src: sourceFile,
|
||||
SrcDivisor: sourceDivisor,
|
||||
}
|
||||
if think != nil {
|
||||
req.Think = think
|
||||
}
|
||||
if caption != "" {
|
||||
req.Caption = &caption
|
||||
}
|
||||
if lyrics != "" {
|
||||
req.Lyrics = &lyrics
|
||||
}
|
||||
if bpm != nil {
|
||||
req.Bpm = bpm
|
||||
}
|
||||
if keyscale != "" {
|
||||
req.Keyscale = &keyscale
|
||||
}
|
||||
if language != "" {
|
||||
req.Language = &language
|
||||
}
|
||||
if timesignature != "" {
|
||||
req.Timesignature = ×ignature
|
||||
}
|
||||
if instrumental != nil {
|
||||
req.Instrumental = instrumental
|
||||
}
|
||||
})
|
||||
|
||||
res, err := soundGenModel.SoundGeneration(context.Background(), req)
|
||||
if err != nil {
|
||||
return "", nil, err
|
||||
}
|
||||
if res != nil && !res.Success {
|
||||
// return RPC error if any
|
||||
if !res.Success {
|
||||
return "", nil, fmt.Errorf("error during sound generation: %s", res.Message)
|
||||
}
|
||||
return filePath, res, nil
|
||||
|
||||
return filePath, res, err
|
||||
}
|
||||
|
||||
@@ -100,9 +100,7 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
|
||||
|
||||
filePath, _, err := backend.SoundGeneration(text,
|
||||
parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
|
||||
inputFile, parseToInt32Ptr(t.InputFileSampleDivisor),
|
||||
nil, "", "", nil, "", "", "", nil,
|
||||
ml, opts, options)
|
||||
inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)
|
||||
|
||||
if err != nil {
|
||||
return err
|
||||
|
||||
@@ -671,8 +671,7 @@ func (c *ModelConfig) GuessUsecases(u ModelConfigUsecase) bool {
|
||||
}
|
||||
|
||||
if (u & FLAG_SOUND_GENERATION) == FLAG_SOUND_GENERATION {
|
||||
soundGenBackends := []string{"transformers-musicgen", "ace-step", "mock-backend"}
|
||||
if !slices.Contains(soundGenBackends, c.Backend) {
|
||||
if c.Backend != "transformers-musicgen" {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
@@ -843,7 +843,7 @@ parameters:
|
||||
Expect(err).ToNot(HaveOccurred(), fmt.Sprint(resp))
|
||||
|
||||
Expect(resp.StatusCode).To(Equal(200), fmt.Sprint(string(dat)))
|
||||
Expect(resp.Header.Get("Content-Type")).To(Or(Equal("audio/x-wav"), Equal("audio/wav"), Equal("audio/vnd.wave")))
|
||||
Expect(resp.Header.Get("Content-Type")).To(Or(Equal("audio/x-wav"), Equal("audio/vnd.wave")))
|
||||
})
|
||||
It("installs and is capable to generate images", Label("stablediffusion"), func() {
|
||||
if runtime.GOOS != "linux" {
|
||||
|
||||
@@ -8,7 +8,6 @@ import (
|
||||
"github.com/mudler/LocalAI/core/config"
|
||||
"github.com/mudler/LocalAI/core/http/middleware"
|
||||
"github.com/mudler/LocalAI/core/schema"
|
||||
"github.com/mudler/LocalAI/pkg/audio"
|
||||
"github.com/mudler/LocalAI/pkg/model"
|
||||
"github.com/mudler/xlog"
|
||||
)
|
||||
@@ -33,30 +32,12 @@ func SoundGenerationEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader
|
||||
|
||||
xlog.Debug("Sound Generation Request about to be sent to backend", "modelFile", "modelFile", "backend", cfg.Backend)
|
||||
|
||||
language := input.Language
|
||||
if language == "" {
|
||||
language = input.VocalLanguage
|
||||
}
|
||||
var bpm *int32
|
||||
if input.BPM != nil {
|
||||
b := int32(*input.BPM)
|
||||
bpm = &b
|
||||
}
|
||||
filePath, _, err := backend.SoundGeneration(
|
||||
input.Text, input.Duration, input.Temperature, input.DoSample,
|
||||
nil, nil,
|
||||
input.Think, input.Caption, input.Lyrics, bpm, input.Keyscale,
|
||||
language, input.Timesignature,
|
||||
input.Instrumental,
|
||||
ml, appConfig, *cfg)
|
||||
// TODO: Support uploading files?
|
||||
filePath, _, err := backend.SoundGeneration(input.Text, input.Duration, input.Temperature, input.DoSample, nil, nil, ml, appConfig, *cfg)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
filePath, contentType := audio.NormalizeAudioFile(filePath)
|
||||
if contentType != "" {
|
||||
c.Response().Header().Set("Content-Type", contentType)
|
||||
}
|
||||
return c.Attachment(filePath, filepath.Base(filePath))
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,7 +8,6 @@ import (
|
||||
"github.com/mudler/LocalAI/core/config"
|
||||
"github.com/mudler/LocalAI/core/http/middleware"
|
||||
"github.com/mudler/LocalAI/core/schema"
|
||||
"github.com/mudler/LocalAI/pkg/audio"
|
||||
"github.com/mudler/LocalAI/pkg/model"
|
||||
"github.com/mudler/xlog"
|
||||
)
|
||||
@@ -40,10 +39,6 @@ func TTSEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
filePath, contentType := audio.NormalizeAudioFile(filePath)
|
||||
if contentType != "" {
|
||||
c.Response().Header().Set("Content-Type", contentType)
|
||||
}
|
||||
return c.Attachment(filePath, filepath.Base(filePath))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -7,11 +7,12 @@ import (
|
||||
"github.com/mudler/LocalAI/core/backend"
|
||||
"github.com/mudler/LocalAI/core/config"
|
||||
"github.com/mudler/LocalAI/core/http/middleware"
|
||||
"github.com/mudler/LocalAI/core/schema"
|
||||
"github.com/mudler/LocalAI/pkg/audio"
|
||||
"github.com/mudler/LocalAI/pkg/model"
|
||||
"github.com/mudler/LocalAI/pkg/utils"
|
||||
|
||||
"github.com/mudler/LocalAI/core/schema"
|
||||
"github.com/mudler/xlog"
|
||||
|
||||
"github.com/mudler/LocalAI/pkg/utils"
|
||||
)
|
||||
|
||||
// TTSEndpoint is the OpenAI Speech API endpoint https://platform.openai.com/docs/api-reference/audio/createSpeech
|
||||
@@ -85,10 +86,6 @@ func TTSEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig
|
||||
return err
|
||||
}
|
||||
|
||||
filePath, contentType := audio.NormalizeAudioFile(filePath)
|
||||
if contentType != "" {
|
||||
c.Response().Header().Set("Content-Type", contentType)
|
||||
}
|
||||
return c.Attachment(filePath, filepath.Base(filePath))
|
||||
}
|
||||
}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user