mirror of
https://github.com/mudler/LocalAI.git
synced 2026-02-03 19:22:39 -05:00
Compare commits
2 Commits
master
...
copilot/fi
| Author | SHA1 | Date | |
|---|---|---|---|
|
6a1e44c8ff | ||
|
|
bda40b266c |
279
.github/workflows/backend.yml
vendored
279
.github/workflows/backend.yml
vendored
@@ -104,45 +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-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"
|
||||
@@ -339,19 +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"
|
||||
@@ -378,45 +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"
|
||||
@@ -665,45 +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"
|
||||
@@ -769,45 +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"
|
||||
@@ -1214,45 +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: ""
|
||||
@@ -1770,19 +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:
|
||||
@@ -1811,64 +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: ${{ matrix.build-type }}
|
||||
|
||||
8
Makefile
8
Makefile
@@ -1,5 +1,5 @@
|
||||
# Disable parallel execution for backend builds
|
||||
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx
|
||||
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx
|
||||
|
||||
GOCMD=go
|
||||
GOTEST=$(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
|
||||
@@ -323,7 +322,6 @@ prepare-test-extra: protogen-python
|
||||
|
||||
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
|
||||
@@ -453,7 +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
|
||||
@@ -502,7 +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)))
|
||||
@@ -525,7 +521,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
|
||||
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-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
|
||||
|
||||
@@ -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
|
||||
@@ -312,7 +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
|
||||
@@ -330,7 +299,6 @@
|
||||
alias: "moonshine"
|
||||
capabilities:
|
||||
nvidia: "cuda12-moonshine"
|
||||
metal: "metal-moonshine"
|
||||
default: "cpu-moonshine"
|
||||
nvidia-cuda-13: "cuda13-moonshine"
|
||||
nvidia-cuda-12: "cuda12-moonshine"
|
||||
@@ -350,7 +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"
|
||||
@@ -373,7 +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"
|
||||
@@ -398,25 +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
|
||||
@@ -455,7 +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"
|
||||
@@ -478,7 +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"
|
||||
@@ -501,7 +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"
|
||||
@@ -523,7 +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"
|
||||
@@ -544,7 +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"
|
||||
@@ -705,234 +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"
|
||||
@@ -1306,7 +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
|
||||
@@ -1374,16 +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"
|
||||
@@ -1391,7 +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"
|
||||
@@ -1433,16 +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"
|
||||
@@ -1450,7 +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"
|
||||
@@ -1492,16 +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"
|
||||
@@ -1601,7 +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"
|
||||
@@ -1652,16 +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"
|
||||
@@ -1669,7 +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"
|
||||
@@ -1701,16 +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"
|
||||
@@ -1749,23 +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"
|
||||
@@ -1809,16 +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
|
||||
@@ -1827,7 +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"
|
||||
@@ -1858,42 +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"
|
||||
@@ -1974,7 +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"
|
||||
@@ -2050,16 +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"
|
||||
@@ -2068,7 +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"
|
||||
@@ -2144,16 +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"
|
||||
@@ -2162,7 +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"
|
||||
@@ -2238,16 +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"
|
||||
@@ -2255,7 +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"
|
||||
@@ -2309,16 +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"
|
||||
@@ -2327,7 +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"
|
||||
@@ -2403,13 +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
|
||||
|
||||
@@ -1,7 +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
|
||||
@@ -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
|
||||
outetts
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
@@ -4,5 +4,6 @@ llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
transformers
|
||||
bitsandbytes
|
||||
outetts
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
@@ -4,5 +4,6 @@ llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
transformers
|
||||
bitsandbytes
|
||||
outetts
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
@@ -5,5 +5,7 @@ transformers
|
||||
llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
bitsandbytes
|
||||
outetts
|
||||
bitsandbytes
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
@@ -5,5 +5,6 @@ llvmlite==0.43.0
|
||||
numba==0.60.0
|
||||
transformers
|
||||
bitsandbytes
|
||||
outetts
|
||||
sentence-transformers==5.2.2
|
||||
protobuf==6.33.5
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -28,7 +28,7 @@ type wrappedModel struct {
|
||||
TTSConfig *config.ModelConfig
|
||||
TranscriptionConfig *config.ModelConfig
|
||||
LLMConfig *config.ModelConfig
|
||||
VADConfig *config.ModelConfig
|
||||
VADConfig *config.ModelConfig
|
||||
|
||||
appConfig *config.ApplicationConfig
|
||||
modelLoader *model.ModelLoader
|
||||
@@ -114,35 +114,6 @@ func (m *wrappedModel) Predict(ctx context.Context, messages schema.Messages, im
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Add noAction function before templating so it's included in the prompt
|
||||
// Allow the user to set custom actions via config file
|
||||
noActionName := "answer"
|
||||
noActionDescription := "use this action to answer without performing any action"
|
||||
|
||||
if m.LLMConfig.FunctionsConfig.NoActionFunctionName != "" {
|
||||
noActionName = m.LLMConfig.FunctionsConfig.NoActionFunctionName
|
||||
}
|
||||
if m.LLMConfig.FunctionsConfig.NoActionDescriptionName != "" {
|
||||
noActionDescription = m.LLMConfig.FunctionsConfig.NoActionDescriptionName
|
||||
}
|
||||
|
||||
noActionGrammar := functions.Function{
|
||||
Name: noActionName,
|
||||
Description: noActionDescription,
|
||||
Parameters: map[string]interface{}{
|
||||
"properties": map[string]interface{}{
|
||||
"message": map[string]interface{}{
|
||||
"type": "string",
|
||||
"description": "The message to reply the user with",
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
if !m.LLMConfig.FunctionsConfig.DisableNoAction {
|
||||
funcs = append(funcs, noActionGrammar)
|
||||
}
|
||||
}
|
||||
|
||||
predInput = m.evaluator.TemplateMessages(input, input.Messages, m.LLMConfig, funcs, len(funcs) > 0)
|
||||
@@ -153,29 +124,38 @@ func (m *wrappedModel) Predict(ctx context.Context, messages schema.Messages, im
|
||||
}
|
||||
}
|
||||
|
||||
// Handle tool_choice parameter similar to the chat endpoint
|
||||
if toolChoice != nil {
|
||||
if toolChoice.Mode != "" {
|
||||
// String values: "auto", "required", "none"
|
||||
switch toolChoice.Mode {
|
||||
case types.ToolChoiceModeRequired:
|
||||
m.LLMConfig.SetFunctionCallString("required")
|
||||
case types.ToolChoiceModeNone:
|
||||
// Don't use tools
|
||||
m.LLMConfig.SetFunctionCallString("none")
|
||||
case types.ToolChoiceModeAuto:
|
||||
// Default behavior - let model decide
|
||||
}
|
||||
} else if toolChoice.Function != nil {
|
||||
// Specific function specified
|
||||
m.LLMConfig.SetFunctionCallString(toolChoice.Function.Name)
|
||||
}
|
||||
}
|
||||
|
||||
// Generate grammar for function calling if tools are provided and grammar generation is enabled
|
||||
shouldUseFn := len(tools) > 0 && m.LLMConfig.ShouldUseFunctions()
|
||||
|
||||
if !m.LLMConfig.FunctionsConfig.GrammarConfig.NoGrammar && shouldUseFn {
|
||||
// Allow the user to set custom actions via config file
|
||||
noActionName := "answer"
|
||||
noActionDescription := "use this action to answer without performing any action"
|
||||
|
||||
if m.LLMConfig.FunctionsConfig.NoActionFunctionName != "" {
|
||||
noActionName = m.LLMConfig.FunctionsConfig.NoActionFunctionName
|
||||
}
|
||||
if m.LLMConfig.FunctionsConfig.NoActionDescriptionName != "" {
|
||||
noActionDescription = m.LLMConfig.FunctionsConfig.NoActionDescriptionName
|
||||
}
|
||||
|
||||
noActionGrammar := functions.Function{
|
||||
Name: noActionName,
|
||||
Description: noActionDescription,
|
||||
Parameters: map[string]interface{}{
|
||||
"properties": map[string]interface{}{
|
||||
"message": map[string]interface{}{
|
||||
"type": "string",
|
||||
"description": "The message to reply the user with",
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
if !m.LLMConfig.FunctionsConfig.DisableNoAction {
|
||||
funcs = append(funcs, noActionGrammar)
|
||||
}
|
||||
|
||||
// Force picking one of the functions by the request
|
||||
if m.LLMConfig.FunctionToCall() != "" {
|
||||
funcs = functions.Functions(funcs).Select(m.LLMConfig.FunctionToCall())
|
||||
@@ -204,7 +184,7 @@ func (m *wrappedModel) Predict(ctx context.Context, messages schema.Messages, im
|
||||
toolChoiceJSON = string(b)
|
||||
}
|
||||
|
||||
return backend.ModelInference(ctx, predInput, messages, images, videos, audios, m.modelLoader, m.LLMConfig, m.confLoader, m.appConfig, tokenCallback, toolsJSON, toolChoiceJSON, logprobs, topLogprobs, logitBias)
|
||||
return backend.ModelInference(ctx, predInput, messages, images, videos, audios, m.modelLoader, m.LLMConfig, m.confLoader, m.appConfig, tokenCallback, toolsJSON, toolChoiceJSON, logprobs, topLogprobs, logitBias, )
|
||||
}
|
||||
|
||||
func (m *wrappedModel) TTS(ctx context.Context, text, voice, language string) (string, *proto.Result, error) {
|
||||
@@ -238,11 +218,11 @@ func newTranscriptionOnlyModel(pipeline *config.Pipeline, cl *config.ModelConfig
|
||||
|
||||
return &transcriptOnlyModel{
|
||||
TranscriptionConfig: cfgSST,
|
||||
VADConfig: cfgVAD,
|
||||
VADConfig: cfgVAD,
|
||||
|
||||
confLoader: cl,
|
||||
confLoader: cl,
|
||||
modelLoader: ml,
|
||||
appConfig: appConfig,
|
||||
appConfig: appConfig,
|
||||
}, cfgSST, nil
|
||||
}
|
||||
|
||||
@@ -317,11 +297,11 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
|
||||
TTSConfig: cfgTTS,
|
||||
TranscriptionConfig: cfgSST,
|
||||
LLMConfig: cfgLLM,
|
||||
VADConfig: cfgVAD,
|
||||
VADConfig: cfgVAD,
|
||||
|
||||
confLoader: cl,
|
||||
confLoader: cl,
|
||||
modelLoader: ml,
|
||||
appConfig: appConfig,
|
||||
evaluator: evaluator,
|
||||
appConfig: appConfig,
|
||||
evaluator: evaluator,
|
||||
}, nil
|
||||
}
|
||||
|
||||
@@ -2456,11 +2456,7 @@ document.addEventListener("alpine:init", () => {
|
||||
|
||||
const N = chat.history.length - 1;
|
||||
if (role === "thinking" || role === "reasoning") {
|
||||
let c = "";
|
||||
const lines = content.split("\n");
|
||||
lines.forEach((line) => {
|
||||
c += DOMPurify.sanitize(marked.parse(line));
|
||||
});
|
||||
const c = DOMPurify.sanitize(marked.parse(content));
|
||||
chat.history.push({ role, content, html: c, image, audio });
|
||||
}
|
||||
else if (chat.history.length && chat.history[N].role === role) {
|
||||
@@ -2475,11 +2471,7 @@ document.addEventListener("alpine:init", () => {
|
||||
chat.history[N].audio = [...(chat.history[N].audio || []), ...audio];
|
||||
}
|
||||
} else {
|
||||
let c = "";
|
||||
const lines = content.split("\n");
|
||||
lines.forEach((line) => {
|
||||
c += DOMPurify.sanitize(marked.parse(line));
|
||||
});
|
||||
const c = DOMPurify.sanitize(marked.parse(content));
|
||||
chat.history.push({
|
||||
role,
|
||||
content,
|
||||
|
||||
@@ -104,3 +104,97 @@ li:last-child {
|
||||
scrollbar-width: thin;
|
||||
scrollbar-color: var(--color-bg-secondary) var(--color-bg-primary);
|
||||
}
|
||||
|
||||
/* Chat message markdown content styles */
|
||||
#messages pre {
|
||||
background-color: var(--color-bg-primary);
|
||||
border: 1px solid var(--color-border-subtle, rgba(255,255,255,0.1));
|
||||
border-radius: 0.5rem;
|
||||
padding: 1rem;
|
||||
overflow-x: auto;
|
||||
max-width: 100%;
|
||||
margin: 0.5rem 0;
|
||||
white-space: pre;
|
||||
}
|
||||
|
||||
#messages pre code {
|
||||
background: transparent;
|
||||
padding: 0;
|
||||
white-space: pre;
|
||||
word-wrap: normal;
|
||||
overflow-wrap: normal;
|
||||
}
|
||||
|
||||
#messages code:not(pre code) {
|
||||
background-color: var(--color-bg-primary);
|
||||
padding: 0.2em 0.4em;
|
||||
border-radius: 3px;
|
||||
font-size: 0.875em;
|
||||
}
|
||||
|
||||
#messages table {
|
||||
width: 100%;
|
||||
border-collapse: collapse;
|
||||
margin: 0.5rem 0;
|
||||
display: block;
|
||||
overflow-x: auto;
|
||||
}
|
||||
|
||||
#messages th,
|
||||
#messages td {
|
||||
border: 1px solid var(--color-border-subtle, rgba(255,255,255,0.1));
|
||||
padding: 0.5rem;
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
#messages th {
|
||||
background-color: var(--color-bg-secondary);
|
||||
}
|
||||
|
||||
#messages blockquote {
|
||||
border-left: 4px solid var(--color-primary);
|
||||
padding-left: 1rem;
|
||||
margin: 0.5rem 0;
|
||||
color: var(--color-text-secondary);
|
||||
}
|
||||
|
||||
#messages h1, #messages h2, #messages h3, #messages h4, #messages h5, #messages h6 {
|
||||
margin-top: 1rem;
|
||||
margin-bottom: 0.5rem;
|
||||
font-weight: 600;
|
||||
line-height: 1.25;
|
||||
}
|
||||
|
||||
#messages h1 { font-size: 1.5rem; }
|
||||
#messages h2 { font-size: 1.25rem; }
|
||||
#messages h3 { font-size: 1.125rem; }
|
||||
#messages h4 { font-size: 1rem; }
|
||||
|
||||
#messages p {
|
||||
margin: 0.5rem 0;
|
||||
}
|
||||
|
||||
#messages ul, #messages ol {
|
||||
margin: 0.5rem 0;
|
||||
padding-left: 1.5rem;
|
||||
}
|
||||
|
||||
#messages hr {
|
||||
border: none;
|
||||
border-top: 1px solid var(--color-border-subtle, rgba(255,255,255,0.1));
|
||||
margin: 1rem 0;
|
||||
}
|
||||
|
||||
/* Mobile responsiveness for chat */
|
||||
@media (max-width: 768px) {
|
||||
#messages {
|
||||
max-width: 100%;
|
||||
padding-left: 0.5rem;
|
||||
padding-right: 0.5rem;
|
||||
}
|
||||
|
||||
#messages pre {
|
||||
max-width: calc(100vw - 3rem);
|
||||
font-size: 0.8rem;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -324,17 +324,11 @@ SOFTWARE.
|
||||
c = DOMPurify.sanitize('<pre><code class="language-json">' + formatted + '</code></pre>');
|
||||
} catch (e) {
|
||||
// If not JSON, treat as markdown
|
||||
const lines = content.split("\n");
|
||||
lines.forEach((line) => {
|
||||
c += DOMPurify.sanitize(marked.parse(line));
|
||||
});
|
||||
c = DOMPurify.sanitize(marked.parse(content));
|
||||
}
|
||||
} else {
|
||||
// For thinking and reasoning, format as markdown
|
||||
const lines = content.split("\n");
|
||||
lines.forEach((line) => {
|
||||
c += DOMPurify.sanitize(marked.parse(line));
|
||||
});
|
||||
c = DOMPurify.sanitize(marked.parse(content));
|
||||
}
|
||||
// Set expanded state: thinking and reasoning are expanded by default in non-MCP mode, collapsed in MCP mode
|
||||
// tool_call and tool_result are always collapsed by default
|
||||
@@ -366,11 +360,7 @@ SOFTWARE.
|
||||
chat.history[N].model = messageModel;
|
||||
}
|
||||
} else {
|
||||
let c = "";
|
||||
const lines = content.split("\n");
|
||||
lines.forEach((line) => {
|
||||
c += DOMPurify.sanitize(marked.parse(line));
|
||||
});
|
||||
const c = DOMPurify.sanitize(marked.parse(content));
|
||||
chat.history.push({
|
||||
role,
|
||||
content,
|
||||
@@ -1332,7 +1322,7 @@ SOFTWARE.
|
||||
<div class="flex flex-col flex-1">
|
||||
<span class="text-xs font-semibold text-[var(--color-text-secondary)] mb-1" x-text="message.model || $store.chat.activeChat()?.model || '{{if .Model}}{{.Model}}{{else}}Assistant{{end}}'"></span>
|
||||
<div class="flex-1 text-[var(--color-text-primary)] flex items-center space-x-2 min-w-0">
|
||||
<div class="p-3 rounded-lg bg-[var(--color-bg-secondary)] border border-[var(--color-accent-border)]/20 shadow-lg max-w-full overflow-x-auto overflow-wrap-anywhere" x-html="message.html"></div>
|
||||
<div class="p-3 rounded-lg bg-[var(--color-bg-secondary)] border border-[var(--color-accent-border)]/20 shadow-lg max-w-full overflow-x-auto break-words" style="overflow-wrap: anywhere; word-break: break-word;" x-html="message.html"></div>
|
||||
<button @click="copyToClipboard(message.html)" title="Copy to clipboard" class="text-[var(--color-text-secondary)] hover:text-[var(--color-primary)] transition-colors p-1 flex-shrink-0">
|
||||
<i class="fa-solid fa-copy"></i>
|
||||
</button>
|
||||
|
||||
@@ -1,29 +1,4 @@
|
||||
---
|
||||
- name: "qwen3-coder-next-mxfp4_moe"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF
|
||||
description: |
|
||||
The model is a quantized version of **Qwen/Qwen3-Coder-Next** (base model) using the **MXFP4** quantization scheme. It is optimized for efficiency while retaining performance, suitable for deployment in applications requiring lightweight inference. The quantized version is tailored for specific tasks, with parameters like temperature=1.0 and top_p=0.95 recommended for generation.
|
||||
overrides:
|
||||
parameters:
|
||||
model: llama-cpp/models/Qwen3-Coder-Next-MXFP4_MOE.gguf
|
||||
name: Qwen3-Coder-Next-MXFP4_MOE-GGUF
|
||||
backend: llama-cpp
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
known_usecases:
|
||||
- chat
|
||||
function:
|
||||
grammar:
|
||||
disable: true
|
||||
description: Imported from https://huggingface.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF
|
||||
options:
|
||||
- use_jinja:true
|
||||
files:
|
||||
- filename: llama-cpp/models/Qwen3-Coder-Next-MXFP4_MOE.gguf
|
||||
sha256: fa356439e87010163778b7eab5f2b07e0e5b7f2cd9aac78b069139f5ae069414
|
||||
uri: https://huggingface.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF/resolve/main/Qwen3-Coder-Next-MXFP4_MOE.gguf
|
||||
- name: "deepseek-ai.deepseek-v3.2"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
@@ -1867,7 +1842,7 @@
|
||||
- gpu
|
||||
- text-to-speech
|
||||
overrides:
|
||||
backend: "outetts"
|
||||
backend: "transformers"
|
||||
name: "outetts"
|
||||
description: "OuteTTS is a 1.6B parameter text to speech model created by OuteAI."
|
||||
parameters:
|
||||
|
||||
Reference in New Issue
Block a user