mirror of
https://github.com/mudler/LocalAI.git
synced 2026-02-02 18:53:32 -05:00
Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
a8057b952c | ||
|
|
fd5c1d916f | ||
|
|
5ce982b9c9 | ||
|
|
47ccfccf7a | ||
|
|
a760f7ff39 | ||
|
|
facf7625f3 | ||
|
|
b3600b3c50 | ||
|
|
f0b47cfe6a | ||
|
|
ee625fc34e | ||
|
|
693aa0b5de | ||
|
|
3973e6e5da | ||
|
|
fb6ec68090 | ||
|
|
0301fc7c46 | ||
|
|
813cb4296d | ||
|
|
deda3a4972 |
2
.github/workflows/image-pr.yml
vendored
2
.github/workflows/image-pr.yml
vendored
@@ -39,7 +39,7 @@ jobs:
|
||||
cuda-minor-version: "0"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-gpu-nvidia-cuda12'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
makeflags: "--jobs=3 --output-sync=target"
|
||||
|
||||
6
.github/workflows/image.yml
vendored
6
.github/workflows/image.yml
vendored
@@ -83,7 +83,7 @@ jobs:
|
||||
cuda-minor-version: "7"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda11'
|
||||
tag-suffix: '-gpu-nvidia-cuda-11'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
makeflags: "--jobs=4 --output-sync=target"
|
||||
@@ -94,7 +94,7 @@ jobs:
|
||||
cuda-minor-version: "0"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda12'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
skip-drivers: 'false'
|
||||
@@ -103,7 +103,7 @@ jobs:
|
||||
- build-type: 'vulkan'
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-vulkan'
|
||||
tag-suffix: '-gpu-vulkan'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
skip-drivers: 'false'
|
||||
|
||||
@@ -72,6 +72,12 @@ RUN <<EOT bash
|
||||
fi
|
||||
EOT
|
||||
|
||||
RUN <<EOT bash
|
||||
if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH}" = "arm64" ]; then
|
||||
echo "nvidia-l4t" > /run/localai/capability
|
||||
fi
|
||||
EOT
|
||||
|
||||
# If we are building with clblas support, we need the libraries for the builds
|
||||
RUN if [ "${BUILD_TYPE}" = "clblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
|
||||
apt-get update && \
|
||||
|
||||
2
Makefile
2
Makefile
@@ -322,7 +322,7 @@ docker-cuda11:
|
||||
--build-arg GO_TAGS="$(GO_TAGS)" \
|
||||
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
|
||||
--build-arg BUILD_TYPE=$(BUILD_TYPE) \
|
||||
-t $(DOCKER_IMAGE)-cuda11 .
|
||||
-t $(DOCKER_IMAGE)-cuda-11 .
|
||||
|
||||
docker-aio:
|
||||
@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"
|
||||
|
||||
@@ -189,10 +189,13 @@ local-ai run https://gist.githubusercontent.com/.../phi-2.yaml
|
||||
local-ai run oci://localai/phi-2:latest
|
||||
```
|
||||
|
||||
> ⚡ **Automatic Backend Detection**: When you install models from the gallery or YAML files, LocalAI automatically detects your system's GPU capabilities (NVIDIA, AMD, Intel) and downloads the appropriate backend. For advanced configuration options, see [GPU Acceleration](https://localai.io/features/gpu-acceleration/#automatic-backend-detection).
|
||||
|
||||
For more information, see [💻 Getting started](https://localai.io/basics/getting_started/index.html)
|
||||
|
||||
## 📰 Latest project news
|
||||
|
||||
- July 2025: All backends migrated outside of the main binary. LocalAI is now more lightweight, small, and automatically downloads the required backend to run the model. [Read the release notes](https://github.com/mudler/LocalAI/releases/tag/v3.2.0)
|
||||
- June 2025: [Backend management](https://github.com/mudler/LocalAI/pull/5607) has been added. Attention: extras images are going to be deprecated from the next release! Read [the backend management PR](https://github.com/mudler/LocalAI/pull/5607).
|
||||
- May 2025: [Audio input](https://github.com/mudler/LocalAI/pull/5466) and [Reranking](https://github.com/mudler/LocalAI/pull/5396) in llama.cpp backend, [Realtime API](https://github.com/mudler/LocalAI/pull/5392), Support to Gemma, SmollVLM, and more multimodal models (available in the gallery).
|
||||
- May 2025: Important: image name changes [See release](https://github.com/mudler/LocalAI/releases/tag/v2.29.0)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
|
||||
LLAMA_VERSION?=a86f52b2859dae4db5a7a0bbc0f1ad9de6b43ec6
|
||||
LLAMA_VERSION?=c7f3169cd523140a288095f2d79befb20a0b73f4
|
||||
LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
|
||||
|
||||
CMAKE_ARGS?=
|
||||
|
||||
@@ -19,7 +19,7 @@ LD_FLAGS?=
|
||||
|
||||
# stablediffusion.cpp (ggml)
|
||||
STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
|
||||
STABLEDIFFUSION_GGML_VERSION?=1896b28ef2fd5b3643120e66979bea487385439f
|
||||
STABLEDIFFUSION_GGML_VERSION?=eed97a5e1d054f9c1e7ac01982ae480411d4157e
|
||||
|
||||
# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
|
||||
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
|
||||
|
||||
@@ -6,7 +6,7 @@ CMAKE_ARGS?=
|
||||
|
||||
# whisper.cpp version
|
||||
WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
|
||||
WHISPER_CPP_VERSION?=1f5cf0b2888402d57bb17b2029b2caa97e5f3baf
|
||||
WHISPER_CPP_VERSION?=7de8dd783f7b2eab56bff6bbc5d3369e34f0e77f
|
||||
|
||||
export WHISPER_CMAKE_ARGS?=-DBUILD_SHARED_LIBS=OFF
|
||||
export WHISPER_DIR=$(abspath ./sources/whisper.cpp)
|
||||
|
||||
@@ -258,6 +258,8 @@
|
||||
icon: https://github.com/PABannier/bark.cpp/raw/main/assets/banner.png
|
||||
name: "bark-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-bark-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-bark-cpp
|
||||
alias: "bark-cpp"
|
||||
- &chatterbox
|
||||
urls:
|
||||
@@ -280,6 +282,8 @@
|
||||
urls:
|
||||
- https://github.com/rhasspy/piper
|
||||
- https://github.com/mudler/go-piper
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-piper
|
||||
license: MIT
|
||||
description: |
|
||||
A fast, local neural text to speech system
|
||||
@@ -292,6 +296,8 @@
|
||||
icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
|
||||
urls:
|
||||
- https://github.com/snakers4/silero-vad
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-silero-vad
|
||||
description: |
|
||||
Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
|
||||
Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
|
||||
@@ -303,6 +309,8 @@
|
||||
- &local-store
|
||||
name: "local-store"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-local-store"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-local-store
|
||||
urls:
|
||||
- https://github.com/mudler/LocalAI
|
||||
description: |
|
||||
@@ -316,6 +324,8 @@
|
||||
- &huggingface
|
||||
name: "huggingface"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-huggingface"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-huggingface
|
||||
icon: https://huggingface.co/front/assets/huggingface_logo-noborder.svg
|
||||
urls:
|
||||
- https://huggingface.co/docs/hub/en/api
|
||||
@@ -328,174 +338,284 @@
|
||||
- !!merge <<: *huggingface
|
||||
name: "huggingface-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-huggingface"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-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 <<: *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 <<: *piper
|
||||
name: "piper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-piper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-piper
|
||||
## llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "darwin-x86-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-darwin-x86-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-darwin-x86-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "darwin-x86-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-darwin-x86-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-darwin-x86-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "nvidia-l4t-arm64-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-arm64-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "nvidia-l4t-arm64-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-arm64-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "cpu-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "cpu-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "cuda11-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "cuda12-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "rocm-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "intel-sycl-f32-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "intel-sycl-f16-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "vulkan-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-vulkan-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "vulkan-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-vulkan-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "metal-llama-cpp"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "metal-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "cuda11-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "cuda12-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "rocm-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "intel-sycl-f32-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-llama-cpp
|
||||
- !!merge <<: *llamacpp
|
||||
name: "intel-sycl-f16-llama-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-llama-cpp"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-llama-cpp
|
||||
## whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "nvidia-l4t-arm64-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-arm64-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "nvidia-l4t-arm64-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-arm64-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "cpu-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "cpu-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "cuda11-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "cuda12-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "rocm-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "intel-sycl-f32-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "intel-sycl-f16-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "vulkan-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-vulkan-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "vulkan-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-vulkan-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "metal-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-metal-darwin-arm64-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "metal-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-metal-darwin-arm64-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "cuda11-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "cuda12-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "rocm-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "intel-sycl-f32-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-whisper
|
||||
- !!merge <<: *whispercpp
|
||||
name: "intel-sycl-f16-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-whisper
|
||||
## stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "cpu-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-cpu-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "cpu-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-cpu-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "vulkan-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-vulkan-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "vulkan-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-vulkan-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "cuda12-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "intel-sycl-f32-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-stablediffusion-ggml"
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "intel-sycl-f16-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "cuda11-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "cuda12-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "intel-sycl-f32-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "intel-sycl-f16-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "cuda11-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "nvidia-l4t-arm64-stablediffusion-ggml-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-nvidia-l4t-arm64-stablediffusion-ggml
|
||||
- !!merge <<: *stablediffusionggml
|
||||
name: "nvidia-l4t-arm64-stablediffusion-ggml"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-stablediffusion-ggml"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-nvidia-l4t-arm64-stablediffusion-ggml
|
||||
# vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "vllm-development"
|
||||
@@ -506,27 +626,43 @@
|
||||
- !!merge <<: *vllm
|
||||
name: "cuda12-vllm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "rocm-vllm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "intel-sycl-f32-vllm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "intel-sycl-f16-vllm"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "cuda12-vllm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "rocm-vllm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "intel-sycl-f32-vllm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-vllm
|
||||
- !!merge <<: *vllm
|
||||
name: "intel-sycl-f16-vllm-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-vllm"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-vllm
|
||||
## Rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "rerankers-development"
|
||||
@@ -537,33 +673,53 @@
|
||||
- !!merge <<: *rerankers
|
||||
name: "cuda11-rerankers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "cuda12-rerankers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "intel-sycl-f32-rerankers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "intel-sycl-f16-rerankers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "rocm-rerankers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "cuda11-rerankers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "cuda12-rerankers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "rocm-rerankers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "intel-sycl-f32-rerankers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-rerankers
|
||||
- !!merge <<: *rerankers
|
||||
name: "intel-sycl-f16-rerankers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rerankers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-rerankers
|
||||
## Transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "transformers-development"
|
||||
@@ -574,33 +730,53 @@
|
||||
- !!merge <<: *transformers
|
||||
name: "cuda12-transformers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "rocm-transformers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "intel-sycl-f32-transformers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "intel-sycl-f16-transformers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "cuda11-transformers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "cuda11-transformers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "cuda12-transformers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "rocm-transformers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "intel-sycl-f32-transformers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-transformers
|
||||
- !!merge <<: *transformers
|
||||
name: "intel-sycl-f16-transformers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-transformers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-transformers
|
||||
## Diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "diffusers-development"
|
||||
@@ -611,27 +787,43 @@
|
||||
- !!merge <<: *diffusers
|
||||
name: "cuda12-diffusers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "rocm-diffusers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "cuda11-diffusers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "intel-sycl-f32-diffusers"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "cuda11-diffusers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "cuda12-diffusers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "rocm-diffusers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-diffusers
|
||||
- !!merge <<: *diffusers
|
||||
name: "intel-sycl-f32-diffusers-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-diffusers"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-diffusers
|
||||
## exllama2
|
||||
- !!merge <<: *exllama2
|
||||
name: "exllama2-development"
|
||||
@@ -642,15 +834,23 @@
|
||||
- !!merge <<: *exllama2
|
||||
name: "cuda11-exllama2"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-exllama2"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-exllama2
|
||||
- !!merge <<: *exllama2
|
||||
name: "cuda12-exllama2"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-exllama2"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-exllama2
|
||||
- !!merge <<: *exllama2
|
||||
name: "cuda11-exllama2-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-exllama2"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-exllama2
|
||||
- !!merge <<: *exllama2
|
||||
name: "cuda12-exllama2-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-exllama2"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-exllama2
|
||||
## kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "kokoro-development"
|
||||
@@ -661,33 +861,53 @@
|
||||
- !!merge <<: *kokoro
|
||||
name: "cuda11-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "cuda12-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "rocm-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "sycl-f32-kokoro"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "sycl-f16-kokoro"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "sycl-f16-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "sycl-f32-kokoro-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "cuda11-kokoro"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "cuda12-kokoro"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-kokoro
|
||||
- !!merge <<: *kokoro
|
||||
name: "rocm-kokoro"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-kokoro"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-kokoro
|
||||
## faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "faster-whisper-development"
|
||||
@@ -698,24 +918,38 @@
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "cuda11-faster-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "cuda12-faster-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "rocm-faster-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "sycl-f32-faster-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "sycl-f16-faster-whisper"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "sycl-f32-faster-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-faster-whisper
|
||||
- !!merge <<: *faster-whisper
|
||||
name: "sycl-f16-faster-whisper-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-faster-whisper"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-faster-whisper
|
||||
## coqui
|
||||
|
||||
- !!merge <<: *coqui
|
||||
@@ -727,33 +961,53 @@
|
||||
- !!merge <<: *coqui
|
||||
name: "cuda11-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "cuda12-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "cuda11-coqui-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "cuda12-coqui-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "rocm-coqui-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "sycl-f32-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "sycl-f16-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "sycl-f32-coqui-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "sycl-f16-coqui-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-coqui
|
||||
- !!merge <<: *coqui
|
||||
name: "rocm-coqui"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-coqui"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-coqui
|
||||
## bark
|
||||
- !!merge <<: *bark
|
||||
name: "bark-development"
|
||||
@@ -764,33 +1018,53 @@
|
||||
- !!merge <<: *bark
|
||||
name: "cuda11-bark-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-bark
|
||||
- !!merge <<: *bark
|
||||
name: "cuda11-bark"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-bark
|
||||
- !!merge <<: *bark
|
||||
name: "rocm-bark-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-rocm-hipblas-bark
|
||||
- !!merge <<: *bark
|
||||
name: "sycl-f32-bark"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f32-bark
|
||||
- !!merge <<: *bark
|
||||
name: "sycl-f16-bark"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-intel-sycl-f16-bark
|
||||
- !!merge <<: *bark
|
||||
name: "sycl-f32-bark-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f32-bark
|
||||
- !!merge <<: *bark
|
||||
name: "sycl-f16-bark-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-intel-sycl-f16-bark
|
||||
- !!merge <<: *bark
|
||||
name: "cuda12-bark"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-bark
|
||||
- !!merge <<: *bark
|
||||
name: "rocm-bark"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-rocm-hipblas-bark
|
||||
- !!merge <<: *bark
|
||||
name: "cuda12-bark-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-bark"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-bark
|
||||
- !!merge <<: *barkcpp
|
||||
name: "bark-cpp-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-bark-cpp"
|
||||
@@ -803,12 +1077,20 @@
|
||||
- !!merge <<: *chatterbox
|
||||
name: "cuda12-chatterbox-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-chatterbox"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-12-chatterbox
|
||||
- !!merge <<: *chatterbox
|
||||
name: "cuda11-chatterbox"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-chatterbox"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-11-chatterbox
|
||||
- !!merge <<: *chatterbox
|
||||
name: "cuda11-chatterbox-development"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-chatterbox"
|
||||
mirrors:
|
||||
- localai/localai-backends:master-gpu-nvidia-cuda-11-chatterbox
|
||||
- !!merge <<: *chatterbox
|
||||
name: "cuda12-chatterbox"
|
||||
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-chatterbox"
|
||||
mirrors:
|
||||
- localai/localai-backends:latest-gpu-nvidia-cuda-12-chatterbox
|
||||
|
||||
@@ -111,7 +111,7 @@ function ensureVenv() {
|
||||
# - requirements-${BUILD_TYPE}.txt
|
||||
# - requirements-${BUILD_PROFILE}.txt
|
||||
#
|
||||
# BUILD_PROFILE is a pore specific version of BUILD_TYPE, ex: cuda11 or cuda12
|
||||
# BUILD_PROFILE is a pore specific version of BUILD_TYPE, ex: cuda-11 or cuda-12
|
||||
# it can also include some options that we do not have BUILD_TYPES for, ex: intel
|
||||
#
|
||||
# NOTE: for BUILD_PROFILE==intel, this function does NOT automatically use the Intel python package index.
|
||||
|
||||
@@ -3,6 +3,7 @@ package gallery
|
||||
import (
|
||||
"github.com/mudler/LocalAI/core/config"
|
||||
"github.com/mudler/LocalAI/pkg/system"
|
||||
"github.com/rs/zerolog/log"
|
||||
)
|
||||
|
||||
// BackendMetadata represents the metadata stored in a JSON file for each installed backend
|
||||
@@ -23,6 +24,7 @@ type GalleryBackend struct {
|
||||
Metadata `json:",inline" yaml:",inline"`
|
||||
Alias string `json:"alias,omitempty" yaml:"alias,omitempty"`
|
||||
URI string `json:"uri,omitempty" yaml:"uri,omitempty"`
|
||||
Mirrors []string `json:"mirrors,omitempty" yaml:"mirrors,omitempty"`
|
||||
CapabilitiesMap map[string]string `json:"capabilities,omitempty" yaml:"capabilities,omitempty"`
|
||||
}
|
||||
|
||||
@@ -33,9 +35,11 @@ func (backend *GalleryBackend) FindBestBackendFromMeta(systemState *system.Syste
|
||||
|
||||
realBackend := backend.CapabilitiesMap[systemState.Capability(backend.CapabilitiesMap)]
|
||||
if realBackend == "" {
|
||||
log.Debug().Str("backend", backend.Name).Str("reportedCapability", systemState.Capability(backend.CapabilitiesMap)).Msg("No backend found for reported capability")
|
||||
return nil
|
||||
}
|
||||
|
||||
log.Debug().Str("backend", backend.Name).Str("reportedCapability", systemState.Capability(backend.CapabilitiesMap)).Msg("Found backend for reported capability")
|
||||
return backends.FindByName(realBackend)
|
||||
}
|
||||
|
||||
|
||||
@@ -146,7 +146,18 @@ func InstallBackend(basePath string, config *GalleryBackend, downloadStatus func
|
||||
|
||||
uri := downloader.URI(config.URI)
|
||||
if err := uri.DownloadFile(backendPath, "", 1, 1, downloadStatus); err != nil {
|
||||
return fmt.Errorf("failed to download backend %q: %v", config.URI, err)
|
||||
success := false
|
||||
// Try to download from mirrors
|
||||
for _, mirror := range config.Mirrors {
|
||||
if err := downloader.URI(mirror).DownloadFile(backendPath, "", 1, 1, downloadStatus); err == nil {
|
||||
success = true
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
if !success {
|
||||
return fmt.Errorf("failed to download backend %q: %v", config.URI, err)
|
||||
}
|
||||
}
|
||||
|
||||
// Create metadata for the backend
|
||||
|
||||
@@ -15,9 +15,10 @@ import (
|
||||
)
|
||||
|
||||
type ModelGalleryEndpointService struct {
|
||||
galleries []config.Gallery
|
||||
modelPath string
|
||||
galleryApplier *services.GalleryService
|
||||
galleries []config.Gallery
|
||||
backendGalleries []config.Gallery
|
||||
modelPath string
|
||||
galleryApplier *services.GalleryService
|
||||
}
|
||||
|
||||
type GalleryModel struct {
|
||||
@@ -25,11 +26,12 @@ type GalleryModel struct {
|
||||
gallery.GalleryModel
|
||||
}
|
||||
|
||||
func CreateModelGalleryEndpointService(galleries []config.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
|
||||
func CreateModelGalleryEndpointService(galleries []config.Gallery, backendGalleries []config.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
|
||||
return ModelGalleryEndpointService{
|
||||
galleries: galleries,
|
||||
modelPath: modelPath,
|
||||
galleryApplier: galleryApplier,
|
||||
galleries: galleries,
|
||||
backendGalleries: backendGalleries,
|
||||
modelPath: modelPath,
|
||||
galleryApplier: galleryApplier,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -79,6 +81,7 @@ func (mgs *ModelGalleryEndpointService) ApplyModelGalleryEndpoint() func(c *fibe
|
||||
ID: uuid.String(),
|
||||
GalleryElementName: input.ID,
|
||||
Galleries: mgs.galleries,
|
||||
BackendGalleries: mgs.backendGalleries,
|
||||
}
|
||||
|
||||
return c.JSON(schema.GalleryResponse{ID: uuid.String(), StatusURL: fmt.Sprintf("%smodels/jobs/%s", utils.BaseURL(c), uuid.String())})
|
||||
|
||||
@@ -23,7 +23,7 @@ func RegisterLocalAIRoutes(router *fiber.App,
|
||||
|
||||
// LocalAI API endpoints
|
||||
if !appConfig.DisableGalleryEndpoint {
|
||||
modelGalleryEndpointService := localai.CreateModelGalleryEndpointService(appConfig.Galleries, appConfig.ModelPath, galleryService)
|
||||
modelGalleryEndpointService := localai.CreateModelGalleryEndpointService(appConfig.Galleries, appConfig.BackendGalleries, appConfig.ModelPath, galleryService)
|
||||
router.Post("/models/apply", modelGalleryEndpointService.ApplyModelGalleryEndpoint())
|
||||
router.Post("/models/delete/:name", modelGalleryEndpointService.DeleteModelGalleryEndpoint())
|
||||
|
||||
|
||||
@@ -180,6 +180,7 @@ func registerGalleryRoutes(app *fiber.App, cl *config.BackendConfigLoader, appCo
|
||||
ID: uid,
|
||||
GalleryElementName: galleryID,
|
||||
Galleries: appConfig.Galleries,
|
||||
BackendGalleries: appConfig.BackendGalleries,
|
||||
}
|
||||
go func() {
|
||||
galleryService.ModelGalleryChannel <- op
|
||||
@@ -219,6 +220,7 @@ func registerGalleryRoutes(app *fiber.App, cl *config.BackendConfigLoader, appCo
|
||||
Delete: true,
|
||||
GalleryElementName: galleryName,
|
||||
Galleries: appConfig.Galleries,
|
||||
BackendGalleries: appConfig.BackendGalleries,
|
||||
}
|
||||
go func() {
|
||||
galleryService.ModelGalleryChannel <- op
|
||||
|
||||
@@ -24,6 +24,7 @@ func (g *GalleryService) backendHandler(op *GalleryOp[gallery.GalleryBackend], s
|
||||
g.modelLoader.DeleteExternalBackend(op.GalleryElementName)
|
||||
} else {
|
||||
log.Warn().Msgf("installing backend %s", op.GalleryElementName)
|
||||
log.Debug().Msgf("backend galleries: %v", g.appConfig.BackendGalleries)
|
||||
err = gallery.InstallBackendFromGallery(g.appConfig.BackendGalleries, systemState, op.GalleryElementName, g.appConfig.BackendsPath, progressCallback, true)
|
||||
if err == nil {
|
||||
err = gallery.RegisterBackends(g.appConfig.BackendsPath, g.modelLoader)
|
||||
|
||||
@@ -15,6 +15,16 @@ This section contains instruction on how to use LocalAI with GPU acceleration.
|
||||
For acceleration for AMD or Metal HW is still in development, for additional details see the [build]({{%relref "docs/getting-started/build#Acceleration" %}})
|
||||
{{% /alert %}}
|
||||
|
||||
## Automatic Backend Detection
|
||||
|
||||
When you install a model from the gallery (or a YAML file), LocalAI intelligently detects the required backend and your system's capabilities, then downloads the correct version for you. Whether you're running on a standard CPU, an NVIDIA GPU, an AMD GPU, or an Intel GPU, LocalAI handles it automatically.
|
||||
|
||||
For advanced use cases or to override auto-detection, you can use the `LOCALAI_FORCE_META_BACKEND_CAPABILITY` environment variable. Here are the available options:
|
||||
|
||||
- `default`: Forces CPU-only backend. This is the fallback if no specific hardware is detected.
|
||||
- `nvidia`: Forces backends compiled with CUDA support for NVIDIA GPUs.
|
||||
- `amd`: Forces backends compiled with ROCm support for AMD GPUs.
|
||||
- `intel`: Forces backends compiled with SYCL/oneAPI support for Intel GPUs.
|
||||
|
||||
## Model configuration
|
||||
|
||||
@@ -71,8 +81,8 @@ To use CUDA, use the images with the `cublas` tag, for example.
|
||||
|
||||
The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=tags):
|
||||
|
||||
- CUDA `11` tags: `master-gpu-nvidia-cuda11`, `v1.40.0-gpu-nvidia-cuda11`, ...
|
||||
- CUDA `12` tags: `master-gpu-nvidia-cuda12`, `v1.40.0-gpu-nvidia-cuda12`, ...
|
||||
- CUDA `11` tags: `master-gpu-nvidia-cuda-11`, `v1.40.0-gpu-nvidia-cuda-11`, ...
|
||||
- CUDA `12` tags: `master-gpu-nvidia-cuda-12`, `v1.40.0-gpu-nvidia-cuda-12`, ...
|
||||
|
||||
In addition to the commands to run LocalAI normally, you need to specify `--gpus all` to docker, for example:
|
||||
|
||||
|
||||
@@ -9,13 +9,11 @@ ico = "rocket_launch"
|
||||
|
||||
### Build
|
||||
|
||||
LocalAI can be built as a container image or as a single, portable binary. Note that some model architectures might require Python libraries, which are not included in the binary. The binary contains only the core backends written in Go and C++.
|
||||
LocalAI can be built as a container image or as a single, portable binary. Note that some model architectures might require Python libraries, which are not included in the binary.
|
||||
|
||||
LocalAI's extensible architecture allows you to add your own backends, which can be written in any language, and as such the container images contains also the Python dependencies to run all the available backends (for example, in order to run backends like __Diffusers__ that allows to generate images and videos from text).
|
||||
|
||||
In some cases you might want to re-build LocalAI from source (for instance to leverage Apple Silicon acceleration), or to build a custom container image with your own backends. This section contains instructions on how to build LocalAI from source.
|
||||
|
||||
|
||||
This section contains instructions on how to build LocalAI from source.
|
||||
|
||||
#### Build LocalAI locally
|
||||
|
||||
@@ -24,7 +22,6 @@ In some cases you might want to re-build LocalAI from source (for instance to le
|
||||
In order to build LocalAI locally, you need the following requirements:
|
||||
|
||||
- Golang >= 1.21
|
||||
- Cmake/make
|
||||
- GCC
|
||||
- GRPC
|
||||
|
||||
@@ -36,20 +33,14 @@ To install the dependencies follow the instructions below:
|
||||
Install `xcode` from the App Store
|
||||
|
||||
```bash
|
||||
brew install abseil cmake go grpc protobuf protoc-gen-go protoc-gen-go-grpc python wget
|
||||
```
|
||||
|
||||
After installing the above dependencies, you need to install grpcio-tools from PyPI. You could do this via a pip --user install or a virtualenv.
|
||||
|
||||
```bash
|
||||
pip install --user grpcio-tools
|
||||
brew install go protobuf protoc-gen-go protoc-gen-go-grpc wget
|
||||
```
|
||||
|
||||
{{% /tab %}}
|
||||
{{% tab tabName="Debian" %}}
|
||||
|
||||
```bash
|
||||
apt install cmake golang libgrpc-dev make protobuf-compiler-grpc python3-grpc-tools
|
||||
apt install golang make protobuf-compiler-grpc
|
||||
```
|
||||
|
||||
After you have golang installed and working, you can install the required binaries for compiling the golang protobuf components via the following commands
|
||||
@@ -63,10 +54,8 @@ go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f1
|
||||
{{% /tab %}}
|
||||
{{% tab tabName="From source" %}}
|
||||
|
||||
Specify `BUILD_GRPC_FOR_BACKEND_LLAMA=true` to build automatically the gRPC dependencies
|
||||
|
||||
```bash
|
||||
make ... BUILD_GRPC_FOR_BACKEND_LLAMA=true build
|
||||
make build
|
||||
```
|
||||
|
||||
{{% /tab %}}
|
||||
@@ -83,36 +72,6 @@ make build
|
||||
|
||||
This should produce the binary `local-ai`
|
||||
|
||||
Here is the list of the variables available that can be used to customize the build:
|
||||
|
||||
| Variable | Default | Description |
|
||||
| ---------------------| ------- | ----------- |
|
||||
| `BUILD_TYPE` | None | Build type. Available: `cublas`, `openblas`, `clblas`, `metal`,`hipblas`, `sycl_f16`, `sycl_f32` |
|
||||
| `GO_TAGS` | `tts stablediffusion` | Go tags. Available: `stablediffusion`, `tts` |
|
||||
| `CLBLAST_DIR` | | Specify a CLBlast directory |
|
||||
| `CUDA_LIBPATH` | | Specify a CUDA library path |
|
||||
| `BUILD_API_ONLY` | false | Set to true to build only the API (no backends will be built) |
|
||||
|
||||
{{% alert note %}}
|
||||
|
||||
#### CPU flagset compatibility
|
||||
|
||||
|
||||
LocalAI uses different backends based on ggml and llama.cpp to run models. If your CPU doesn't support common instruction sets, you can disable them during build:
|
||||
|
||||
```
|
||||
CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_AVX=OFF -DGGML_FMA=OFF" make build
|
||||
```
|
||||
|
||||
To have effect on the container image, you need to set `REBUILD=true`:
|
||||
|
||||
```
|
||||
docker run quay.io/go-skynet/localai
|
||||
docker run --rm -ti -p 8080:8080 -e DEBUG=true -e MODELS_PATH=/models -e THREADS=1 -e REBUILD=true -e CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_AVX=OFF -DGGML_FMA=OFF" -v $PWD/models:/models quay.io/go-skynet/local-ai:latest
|
||||
```
|
||||
|
||||
{{% /alert %}}
|
||||
|
||||
#### Container image
|
||||
|
||||
Requirements:
|
||||
@@ -153,6 +112,9 @@ wget https://huggingface.co/TheBloke/phi-2-GGUF/resolve/main/phi-2.Q2_K.gguf -O
|
||||
# Use a template from the examples
|
||||
cp -rf prompt-templates/ggml-gpt4all-j.tmpl models/phi-2.Q2_K.tmpl
|
||||
|
||||
# Install the llama-cpp backend
|
||||
./local-ai backends install llama-cpp
|
||||
|
||||
# Run LocalAI
|
||||
./local-ai --models-path=./models/ --debug=true
|
||||
|
||||
@@ -186,131 +148,53 @@ sudo xcode-select --switch /Applications/Xcode.app/Contents/Developer
|
||||
|
||||
```
|
||||
# reinstall build dependencies
|
||||
brew reinstall abseil cmake go grpc protobuf wget
|
||||
brew reinstall go grpc protobuf wget
|
||||
|
||||
make clean
|
||||
|
||||
make build
|
||||
```
|
||||
|
||||
**Requirements**: OpenCV, Gomp
|
||||
## Build backends
|
||||
|
||||
Image generation requires `GO_TAGS=stablediffusion` to be set during build:
|
||||
LocalAI have several backends available for installation in the backend gallery. The backends can be also built by source. As backends might vary from language and dependencies that they require, the documentation will provide generic guidance for few of the backends, which can be applied with some slight modifications also to the others.
|
||||
|
||||
### Manually
|
||||
|
||||
Typically each backend include a Makefile which allow to package the backend.
|
||||
|
||||
In the LocalAI repository, for instance you can build `bark-cpp` by doing:
|
||||
|
||||
```
|
||||
make GO_TAGS=stablediffusion build
|
||||
git clone https://github.com/go-skynet/LocalAI.git
|
||||
|
||||
# Build the bark-cpp backend (requires cmake)
|
||||
make -C LocalAI/backend/go/bark-cpp build package
|
||||
|
||||
# Build vllm backend (requires python)
|
||||
make -C LocalAI/backend/python/vllm
|
||||
```
|
||||
|
||||
### Build with Text to audio support
|
||||
### With Docker
|
||||
|
||||
**Requirements**: piper-phonemize
|
||||
Building with docker is simpler as abstracts away all the requirement, and focuses on building the final OCI images that are available in the gallery. This allows for instance also to build locally a backend and install it with LocalAI. You can refer to [Backends](https://localai.io/backends/) for general guidance on how to install and develop backends.
|
||||
|
||||
Text to audio support is experimental and requires `GO_TAGS=tts` to be set during build:
|
||||
In the LocalAI repository, you can build `bark-cpp` by doing:
|
||||
|
||||
```
|
||||
make GO_TAGS=tts build
|
||||
git clone https://github.com/go-skynet/LocalAI.git
|
||||
|
||||
# Build the bark-cpp backend (requires docker)
|
||||
make docker-build-bark-cpp
|
||||
```
|
||||
|
||||
### Acceleration
|
||||
|
||||
#### OpenBLAS
|
||||
|
||||
Software acceleration.
|
||||
|
||||
Requirements: OpenBLAS
|
||||
|
||||
```
|
||||
make BUILD_TYPE=openblas build
|
||||
```
|
||||
|
||||
#### CuBLAS
|
||||
|
||||
Nvidia Acceleration.
|
||||
|
||||
Requirement: Nvidia CUDA toolkit
|
||||
|
||||
Note: CuBLAS support is experimental, and has not been tested on real HW. please report any issues you find!
|
||||
|
||||
```
|
||||
make BUILD_TYPE=cublas build
|
||||
```
|
||||
|
||||
More informations available in the upstream PR: https://github.com/ggerganov/llama.cpp/pull/1412
|
||||
|
||||
|
||||
#### Hipblas (AMD GPU with ROCm on Arch Linux)
|
||||
|
||||
Packages:
|
||||
```
|
||||
pacman -S base-devel git rocm-hip-sdk rocm-opencl-sdk opencv clblast grpc
|
||||
```
|
||||
|
||||
Library links:
|
||||
```
|
||||
export CGO_CFLAGS="-I/usr/include/opencv4"
|
||||
export CGO_CXXFLAGS="-I/usr/include/opencv4"
|
||||
export CGO_LDFLAGS="-L/opt/rocm/hip/lib -lamdhip64 -L/opt/rocm/lib -lOpenCL -L/usr/lib -lclblast -lrocblas -lhipblas -lrocrand -lomp -O3 --rtlib=compiler-rt -unwindlib=libgcc -lhipblas -lrocblas --hip-link"
|
||||
```
|
||||
|
||||
Build:
|
||||
```
|
||||
make BUILD_TYPE=hipblas GPU_TARGETS=gfx1030
|
||||
```
|
||||
|
||||
#### ClBLAS
|
||||
|
||||
AMD/Intel GPU acceleration.
|
||||
|
||||
Requirement: OpenCL, CLBlast
|
||||
|
||||
```
|
||||
make BUILD_TYPE=clblas build
|
||||
```
|
||||
|
||||
To specify a clblast dir set: `CLBLAST_DIR`
|
||||
|
||||
#### Intel GPU acceleration
|
||||
|
||||
Intel GPU acceleration is supported via SYCL.
|
||||
|
||||
Requirements: [Intel oneAPI Base Toolkit](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html) (see also [llama.cpp setup installations instructions](https://github.com/ggerganov/llama.cpp/blob/d71ac90985854b0905e1abba778e407e17f9f887/README-sycl.md?plain=1#L56))
|
||||
|
||||
```
|
||||
make BUILD_TYPE=sycl_f16 build # for float16
|
||||
make BUILD_TYPE=sycl_f32 build # for float32
|
||||
```
|
||||
|
||||
#### Metal (Apple Silicon)
|
||||
|
||||
```
|
||||
make build
|
||||
|
||||
# correct build type is automatically used on mac (BUILD_TYPE=metal)
|
||||
# Set `gpu_layers: 256` (or equal to the number of model layers) to your YAML model config file and `f16: true`
|
||||
```
|
||||
|
||||
### Windows compatibility
|
||||
|
||||
Make sure to give enough resources to the running container. See https://github.com/go-skynet/LocalAI/issues/2
|
||||
|
||||
### Examples
|
||||
|
||||
More advanced build options are available, for instance to build only a single backend.
|
||||
|
||||
#### Build only a single backend
|
||||
|
||||
You can control the backends that are built by setting the `GRPC_BACKENDS` environment variable. For instance, to build only the `llama-cpp` backend only:
|
||||
Note that `make` is only by convenience, in reality it just runs a simple `docker` command as:
|
||||
|
||||
```bash
|
||||
make GRPC_BACKENDS=backend-assets/grpc/llama-cpp build
|
||||
docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:bark-cpp -f LocalAI/backend/Dockerfile.golang --build-arg BACKEND=bark-cpp .
|
||||
```
|
||||
|
||||
By default, all the backends are built.
|
||||
Note:
|
||||
|
||||
#### Specific llama.cpp version
|
||||
|
||||
To build with a specific version of llama.cpp, set `CPPLLAMA_VERSION` to the tag or wanted sha:
|
||||
|
||||
```
|
||||
CPPLLAMA_VERSION=<sha> make build
|
||||
```
|
||||
- BUILD_TYPE can be either: `cublas`, `hipblas`, `sycl_f16`, `sycl_f32`, `metal`.
|
||||
- BASE_IMAGE is tested on `ubuntu:22.04` (and defaults to it)
|
||||
@@ -163,9 +163,9 @@ Standard container images do not have pre-installed models.
|
||||
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda11` | `localai/localai:master-gpu-nvidia-cuda11` |
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda-11` | `localai/localai:master-gpu-nvidia-cuda-11` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-nvidia-cuda-11` | `localai/localai:latest-gpu-nvidia-cuda-11` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda11` | `localai/localai:{{< version >}}-gpu-nvidia-cuda11` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda-11` | `localai/localai:{{< version >}}-gpu-nvidia-cuda-11` |
|
||||
|
||||
{{% /tab %}}
|
||||
|
||||
@@ -173,9 +173,9 @@ Standard container images do not have pre-installed models.
|
||||
|
||||
| Description | Quay | Docker Hub |
|
||||
| --- | --- |-------------------------------------------------------------|
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda12` | `localai/localai:master-gpu-nvidia-cuda12` |
|
||||
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda-12` | `localai/localai:master-gpu-nvidia-cuda12` |
|
||||
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-nvidia-cuda-12` | `localai/localai:latest-gpu-nvidia-cuda-12` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda12` | `localai/localai:{{< version >}}-gpu-nvidia-cuda12` |
|
||||
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda-12` | `localai/localai:{{< version >}}-gpu-nvidia-cuda-12` |
|
||||
|
||||
{{% /tab %}}
|
||||
|
||||
|
||||
@@ -106,6 +106,9 @@ local-ai run https://gist.githubusercontent.com/.../phi-2.yaml
|
||||
local-ai run oci://localai/phi-2:latest
|
||||
```
|
||||
|
||||
{{% alert icon="⚡" %}}
|
||||
**Automatic Backend Detection**: When you install models from the gallery or YAML files, LocalAI automatically detects your system's GPU capabilities (NVIDIA, AMD, Intel) and downloads the appropriate backend. For advanced configuration options, see [GPU Acceleration]({{% relref "docs/features/gpu-acceleration#automatic-backend-detection" %}}).
|
||||
{{% /alert %}}
|
||||
|
||||
For a full list of options, refer to the [Installer Options]({{% relref "docs/advanced/installer" %}}) documentation.
|
||||
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
{
|
||||
"version": "v3.1.1"
|
||||
"version": "v3.2.1"
|
||||
}
|
||||
|
||||
10
docs/static/install.sh
vendored
10
docs/static/install.sh
vendored
@@ -660,7 +660,7 @@ install_docker() {
|
||||
|
||||
IMAGE_TAG=
|
||||
if [ "$USE_VULKAN" = true ]; then
|
||||
IMAGE_TAG=${LOCALAI_VERSION}-vulkan
|
||||
IMAGE_TAG=${LOCALAI_VERSION}-gpu-vulkan
|
||||
|
||||
info "Starting LocalAI Docker container..."
|
||||
$SUDO docker run -v local-ai-data:/models \
|
||||
@@ -672,7 +672,7 @@ install_docker() {
|
||||
-d -p $PORT:8080 --name local-ai localai/localai:$IMAGE_TAG $STARTCOMMAND
|
||||
elif [ "$HAS_CUDA" ]; then
|
||||
# Default to CUDA 12
|
||||
IMAGE_TAG=${LOCALAI_VERSION}-gpu-nvidia-cuda12
|
||||
IMAGE_TAG=${LOCALAI_VERSION}-gpu-nvidia-cuda-12
|
||||
# AIO
|
||||
if [ "$USE_AIO" = true ]; then
|
||||
IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-nvidia-cuda-12
|
||||
@@ -757,7 +757,7 @@ install_binary_darwin() {
|
||||
[ "$(uname -s)" = "Darwin" ] || fatal 'This script is intended to run on macOS only.'
|
||||
|
||||
info "Downloading LocalAI ${LOCALAI_VERSION}..."
|
||||
curl --fail --show-error --location --progress-bar -o $TEMP_DIR/local-ai "https://github.com/mudler/LocalAI/releases/download/${LOCALAI_VERSION}/local-ai-Darwin-${ARCH}"
|
||||
curl --fail --show-error --location --progress-bar -o $TEMP_DIR/local-ai "https://github.com/mudler/LocalAI/releases/download/${LOCALAI_VERSION}/local-ai-${LOCALAI_VERSION}-darwin-${ARCH}"
|
||||
|
||||
info "Installing to /usr/local/bin/local-ai"
|
||||
install -o0 -g0 -m755 $TEMP_DIR/local-ai /usr/local/bin/local-ai
|
||||
@@ -789,7 +789,7 @@ install_binary() {
|
||||
fi
|
||||
|
||||
info "Downloading LocalAI ${LOCALAI_VERSION}..."
|
||||
curl --fail --location --progress-bar -o $TEMP_DIR/local-ai "https://github.com/mudler/LocalAI/releases/download/${LOCALAI_VERSION}/local-ai-Linux-${ARCH}"
|
||||
curl --fail --location --progress-bar -o $TEMP_DIR/local-ai "https://github.com/mudler/LocalAI/releases/download/${LOCALAI_VERSION}/local-ai-${LOCALAI_VERSION}-linux-${ARCH}"
|
||||
|
||||
for BINDIR in /usr/local/bin /usr/bin /bin; do
|
||||
echo $PATH | grep -q $BINDIR && break || continue
|
||||
@@ -868,7 +868,7 @@ OS="$(uname -s)"
|
||||
|
||||
ARCH=$(uname -m)
|
||||
case "$ARCH" in
|
||||
x86_64) ARCH="x86_64" ;;
|
||||
x86_64) ARCH="amd64" ;;
|
||||
aarch64|arm64) ARCH="arm64" ;;
|
||||
*) fatal "Unsupported architecture: $ARCH" ;;
|
||||
esac
|
||||
|
||||
@@ -25,20 +25,24 @@ func (s *SystemState) Capability(capMap map[string]string) string {
|
||||
|
||||
// Check if the reported capability is in the map
|
||||
if _, exists := capMap[reportedCapability]; exists {
|
||||
log.Debug().Str("reportedCapability", reportedCapability).Any("capMap", capMap).Msg("Using reported capability")
|
||||
return reportedCapability
|
||||
}
|
||||
|
||||
log.Debug().Str("reportedCapability", reportedCapability).Any("capMap", capMap).Msg("The requested capability was not found, using default capability")
|
||||
// Otherwise, return the default capability (catch-all)
|
||||
return defaultCapability
|
||||
}
|
||||
|
||||
func (s *SystemState) getSystemCapabilities() string {
|
||||
if os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY") != "" {
|
||||
log.Debug().Str("LOCALAI_FORCE_META_BACKEND_CAPABILITY", os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY")).Msg("Using forced capability")
|
||||
return os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY")
|
||||
}
|
||||
|
||||
capabilityRunFile := "/run/localai/capability"
|
||||
if os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE") != "" {
|
||||
log.Debug().Str("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE", os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE")).Msg("Using forced capability run file")
|
||||
capabilityRunFile = os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE")
|
||||
}
|
||||
|
||||
@@ -48,31 +52,37 @@ func (s *SystemState) getSystemCapabilities() string {
|
||||
if _, err := os.Stat(capabilityRunFile); err == nil {
|
||||
capability, err := os.ReadFile(capabilityRunFile)
|
||||
if err == nil {
|
||||
return string(capability)
|
||||
log.Debug().Str("capability", string(capability)).Msg("Using capability from run file")
|
||||
return strings.Trim(strings.TrimSpace(string(capability)), "\n")
|
||||
}
|
||||
}
|
||||
|
||||
// If we are on mac and arm64, we will return metal
|
||||
if runtime.GOOS == "darwin" && runtime.GOARCH == "arm64" {
|
||||
log.Debug().Msg("Using metal capability")
|
||||
return metal
|
||||
}
|
||||
|
||||
// If we are on mac and x86, we will return darwin-x86
|
||||
if runtime.GOOS == "darwin" && runtime.GOARCH == "amd64" {
|
||||
log.Debug().Msg("Using darwin-x86 capability")
|
||||
return darwinX86
|
||||
}
|
||||
|
||||
// If arm64 on linux and a nvidia gpu is detected, we will return nvidia-l4t
|
||||
if runtime.GOOS == "linux" && runtime.GOARCH == "arm64" {
|
||||
if s.GPUVendor == "nvidia" {
|
||||
log.Debug().Msg("Using nvidia-l4t capability")
|
||||
return nvidiaL4T
|
||||
}
|
||||
}
|
||||
|
||||
if s.GPUVendor == "" {
|
||||
log.Debug().Msg("Using default capability")
|
||||
return defaultCapability
|
||||
}
|
||||
|
||||
log.Debug().Str("GPUVendor", s.GPUVendor).Msg("Using GPU vendor capability")
|
||||
return s.GPUVendor
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user