mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-04-08 00:38:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(intel): Set GPU vendor on Intel images and cleanup (#5945)

Browse Source 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
This commit is contained in:
Richard Palethorpe
2025-07-31 18:44:46 +01:00
committed by GitHub
parent 173e0774c0
commit c07bc55fee
13 changed files with 29 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/image-pr.yml vendored
View File

@@ -51,12 +51,12 @@ jobs:
grpc-base-image: "ubuntu:22.04"
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'sycl_f16'
- build-type: 'sycl'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: 'sycl-f16'
tag-suffix: 'sycl'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'vulkan'

15
.github/workflows/image.yml vendored
View File

@@ -109,24 +109,15 @@ jobs:
skip-drivers: 'false'
makeflags: "--jobs=4 --output-sync=target"
aio: "-aio-gpu-vulkan"
- build-type: 'sycl_f16'
- build-type: 'sycl'
platforms: 'linux/amd64'
tag-latest: 'auto'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-gpu-intel-f16'
tag-suffix: '-gpu-intel'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
aio: "-aio-gpu-intel-f16"
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'auto'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-gpu-intel-f32'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
aio: "-aio-gpu-intel-f32"
aio: "-aio-gpu-intel"
gh-runner:
uses: ./.github/workflows/image_build.yml

5
Dockerfile
View File

@@ -100,6 +100,11 @@ RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
ldconfig \
; fi
RUN expr "${BUILD_TYPE}" : sycl && \
echo "intel" > /run/localai/capability || \
echo "Not Intel"
# Cuda
ENV PATH=/usr/local/cuda/bin:${PATH}

14
Makefile
View File

@@ -5,8 +5,6 @@ BINARY_NAME=local-ai
GORELEASER?=
ONEAPI_VERSION?=2025.2
export BUILD_TYPE?=
GO_TAGS?=
@@ -340,19 +338,11 @@ docker-aio-all:
docker-image-intel:
docker build \
--build-arg BASE_IMAGE=intel/oneapi-basekit:${ONEAPI_VERSION}.0-0-devel-ubuntu24.04 \
--build-arg BASE_IMAGE=quay.io/go-skynet/intel-oneapi-base:latest \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="$(GO_TAGS)" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
--build-arg BUILD_TYPE=sycl_f32 -t $(DOCKER_IMAGE) .
docker-image-intel-xpu:
docker build \
--build-arg BASE_IMAGE=intel/oneapi-basekit:${ONEAPI_VERSION}.0-0-devel-ubuntu22.04 \
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
--build-arg GO_TAGS="$(GO_TAGS)" \
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
--build-arg BUILD_TYPE=sycl_f32 -t $(DOCKER_IMAGE) .
--build-arg BUILD_TYPE=sycl -t $(DOCKER_IMAGE) .
########################################################
## Backends

8
README.md
View File

@@ -140,11 +140,7 @@ docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri
### Intel GPU Images (oneAPI):
```bash
# Intel GPU with FP16 support
docker run -ti --name local-ai -p 8080:8080 --device=/dev/dri/card1 --device=/dev/dri/renderD128 localai/localai:latest-gpu-intel-f16
# Intel GPU with FP32 support
docker run -ti --name local-ai -p 8080:8080 --device=/dev/dri/card1 --device=/dev/dri/renderD128 localai/localai:latest-gpu-intel-f32
docker run -ti --name local-ai -p 8080:8080 --device=/dev/dri/card1 --device=/dev/dri/renderD128 localai/localai:latest-gpu-intel
```
### Vulkan GPU Images:
@@ -166,7 +162,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-11
# Intel GPU version
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel-f16
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel
# AMD GPU version
docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas

11
backend/Dockerfile.golang
View File

@@ -96,17 +96,6 @@ RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
ldconfig \
; fi
# Intel oneAPI requirements
RUN <<EOT bash
if [[ "${BUILD_TYPE}" == sycl* ]] && [ "${SKIP_DRIVERS}" = "false" ]; then
apt-get update && \
apt-get install -y --no-install-recommends \
intel-oneapi-runtime-libs && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
fi
EOT
# Install Go
RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | tar -C /usr/local -xz
ENV PATH=$PATH:/root/go/bin:/usr/local/go/bin:/usr/local/bin

2
backend/cpp/llama-cpp/Makefile
View File

@@ -26,7 +26,7 @@ else ifeq ($(BUILD_TYPE),openblas)
# If build type is clblas (openCL) we set -DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
else ifeq ($(BUILD_TYPE),clblas)
CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
else ifeq ($(BUILD_TYPE),hipblas)
ROCM_HOME ?= /opt/rocm
ROCM_PATH ?= /opt/rocm

2
docs/content/docs/advanced/advanced-usage.md
View File

@@ -448,7 +448,7 @@ there are additional environment variables available that modify the behavior of
| Environment variable | Default | Description |
|----------------------------|---------|------------------------------------------------------------------------------------------------------------|
| `REBUILD` | `false` | Rebuild LocalAI on startup |
| `BUILD_TYPE` | | Build type. Available: `cublas`, `openblas`, `clblas` |
| `BUILD_TYPE` | | Build type. Available: `cublas`, `openblas`, `clblas`, `intel` (intel core), `sycl_f16`, `sycl_f32` (intel backends) |
| `GO_TAGS` | | Go tags. Available: `stablediffusion` |
| `HUGGINGFACEHUB_API_TOKEN` | | Special token for interacting with HuggingFace Inference API, required only when using the `langchain-huggingface` backend |
| `EXTRA_BACKENDS` | | A space separated list of backends to prepare. For example `EXTRA_BACKENDS="backend/python/diffusers backend/python/transformers"` prepares the python environment on start |

6
docs/content/docs/features/GPU-acceleration.md
View File

@@ -267,7 +267,7 @@ If building from source, you need to install [Intel oneAPI Base Toolkit](https:/
### Container images
To use SYCL, use the images with the `gpu-intel-f16` or `gpu-intel-f32` tag, for example `{{< version >}}-gpu-intel-f32-core`, `{{< version >}}-gpu-intel-f16`, ...
To use SYCL, use the images with `gpu-intel` in the tag, for example `{{< version >}}-gpu-intel`, ...
The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=tags).
@@ -276,7 +276,7 @@ The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=ta
To run LocalAI with Docker and sycl starting `phi-2`, you can use the following command as an example:
```bash
docker run -e DEBUG=true --privileged -ti -v $PWD/models:/models -p 8080:8080 -v /dev/dri:/dev/dri --rm quay.io/go-skynet/local-ai:master-gpu-intel-f32 phi-2
docker run -e DEBUG=true --privileged -ti -v $PWD/models:/models -p 8080:8080 -v /dev/dri:/dev/dri --rm quay.io/go-skynet/local-ai:master-gpu-intel phi-2
```
### Notes
@@ -284,7 +284,7 @@ docker run -e DEBUG=true --privileged -ti -v $PWD/models:/models -p 8080:8080 -
In addition to the commands to run LocalAI normally, you need to specify `--device /dev/dri` to docker, for example:
```bash
docker run --rm -ti --device /dev/dri -p 8080:8080 -e DEBUG=true -e MODELS_PATH=/models -e THREADS=1 -v $PWD/models:/models quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel-f16
docker run --rm -ti --device /dev/dri -p 8080:8080 -e DEBUG=true -e MODELS_PATH=/models -e THREADS=1 -v $PWD/models:/models quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel
```
Note also that sycl does have a known issue to hang with `mmap: true`. You have to disable it in the model configuration if explicitly enabled.

2
docs/content/docs/getting-started/build.md
View File

@@ -197,4 +197,4 @@ docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_
Note:
- BUILD_TYPE can be either: `cublas`, `hipblas`, `sycl_f16`, `sycl_f32`, `metal`.
- BASE_IMAGE is tested on `ubuntu:22.04` (and defaults to it)
- BASE_IMAGE is tested on `ubuntu:22.04` (and defaults to it) and `quay.io/go-skynet/intel-oneapi-base:latest` for intel/sycl

21
docs/content/docs/getting-started/container-images.md
View File

@@ -131,8 +131,7 @@ docker run -p 8080:8080 --name local-ai -ti -v localai-models:/models localai/lo
| Latest images for Nvidia GPU (CUDA11) | `quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-11` | `localai/localai:latest-aio-gpu-nvidia-cuda-11` |
| Latest images for Nvidia GPU (CUDA12) | `quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-12` | `localai/localai:latest-aio-gpu-nvidia-cuda-12` |
| Latest images for AMD GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-hipblas` | `localai/localai:latest-aio-gpu-hipblas` |
| Latest images for Intel GPU (sycl f16) | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel-f16` | `localai/localai:latest-aio-gpu-intel-f16` |
| Latest images for Intel GPU (sycl f32) | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel-f32` | `localai/localai:latest-aio-gpu-intel-f32` |
| Latest images for Intel GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel` | `localai/localai:latest-aio-gpu-intel` |
### Available environment variables
@@ -179,23 +178,13 @@ Standard container images do not have pre-installed models.
{{% /tab %}}
{{% tab tabName="Intel GPU (sycl f16)" %}}
{{% tab tabName="Intel GPU" %}}
| Description | Quay | Docker Hub |
| --- | --- |-------------------------------------------------------------|
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-intel-f16` | `localai/localai:master-gpu-intel-f16` |
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel-f16` | `localai/localai:latest-gpu-intel-f16` |
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel-f16` | `localai/localai:{{< version >}}-gpu-intel-f16` |
{{% /tab %}}
{{% tab tabName="Intel GPU (sycl f32)" %}}
| Description | Quay | Docker Hub |
| --- | --- |-------------------------------------------------------------|
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-intel-f32` | `localai/localai:master-gpu-intel-f32` |
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel-f32` | `localai/localai:latest-gpu-intel-f32` |
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel-f32` | `localai/localai:{{< version >}}-gpu-intel-f32` |
| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-intel` | `localai/localai:master-gpu-intel` |
| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel` | `localai/localai:latest-gpu-intel` |
| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel` | `localai/localai:{{< version >}}-gpu-intel` |
{{% /tab %}}

8
docs/content/docs/getting-started/quickstart.md
View File

@@ -59,11 +59,7 @@ docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri
#### Intel GPU Images (oneAPI):
```bash
# Intel GPU with FP16 support
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel-f16
# Intel GPU with FP32 support
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel-f32
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel
```
#### Vulkan GPU Images:
@@ -85,7 +81,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-11
# Intel GPU version
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel-f16
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel
# AMD GPU version
docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas

5
docs/static/install.sh vendored
View File

@@ -715,11 +715,10 @@ install_docker() {
$envs \
-d -p $PORT:8080 --name local-ai localai/localai:$IMAGE_TAG $STARTCOMMAND
elif [ "$HAS_INTEL" ]; then
# Default to FP32 for better compatibility
IMAGE_TAG=${LOCALAI_VERSION}-gpu-intel-f32
IMAGE_TAG=${LOCALAI_VERSION}-gpu-intel
# AIO
if [ "$USE_AIO" = true ]; then
IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-intel-f32
IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-intel
fi
info "Starting LocalAI Docker container..."