-ARG ONEAPI_VERSION=2025.3.2-0-devel-ubuntu24.04
+ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04
## Build Image
--- /dev/null
+name: CI (sycl)
+
+on:
+ workflow_dispatch: # allows manual triggering
+ push:
+ branches:
+ - master
+ paths: [
+ '.github/workflows/build-sycl.yml',
+ '**/CMakeLists.txt',
+ '**/.cmake',
+ '**/*.h',
+ '**/*.hpp',
+ '**/*.c',
+ '**/*.cpp'
+ ]
+
+ pull_request:
+ types: [opened, synchronize, reopened]
+ paths: [
+ '.github/workflows/build-sycl.yml',
+ 'ggml/src/ggml-sycl/**'
+ ]
+
+concurrency:
+ group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+ cancel-in-progress: true
+
+env:
+ GGML_NLOOP: 3
+ GGML_N_THREADS: 1
+ LLAMA_LOG_COLORS: 1
+ LLAMA_LOG_PREFIX: 1
+ LLAMA_LOG_TIMESTAMPS: 1
+
+jobs:
+
+ ubuntu-24-sycl:
+ strategy:
+ matrix:
+ build: [fp32, fp16]
+ include:
+ - build: fp32
+ fp16: OFF
+ - build: fp16
+ fp16: ON
+
+ runs-on: ubuntu-24.04
+
+ env:
+ ONEAPI_ROOT: /opt/intel/oneapi/
+ ONEAPI_INSTALLER_VERSION: "2025.3.3"
+
+ continue-on-error: true
+
+ steps:
+ - uses: actions/checkout@v6
+
+ - name: Use oneAPI Installation Cache
+ uses: actions/cache@v5
+ id: cache-sycl
+ with:
+ path: ${{ env.ONEAPI_ROOT }}
+ key: oneAPI-${{ env.ONEAPI_INSTALLER_VERSION }}-${{ runner.os }}
+
+ - name: Download & Install oneAPI
+ shell: bash
+ if: steps.cache-sycl.outputs.cache-hit != 'true'
+ run: |
+ cd /tmp
+ wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh
+ sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: ubuntu-24-sycl-${{ matrix.build }}
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build
+ id: cmake_build
+ run: |
+ source /opt/intel/oneapi/setvars.sh
+ cmake -B build \
+ -G "Ninja" \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DGGML_SYCL=ON \
+ -DCMAKE_C_COMPILER=icx \
+ -DCMAKE_CXX_COMPILER=icpx \
+ -DLLAMA_OPENSSL=OFF \
+ -DGGML_NATIVE=OFF \
+ -DGGML_SYCL_F16=${{ matrix.fp16 }}
+ time cmake --build build --config Release -j $(nproc)
+
+ windows-latest-sycl:
+ runs-on: windows-2022
+
+ defaults:
+ run:
+ shell: bash
+
+ env:
+ WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b60765d1-2b85-4e85-86b6-cb0e9563a699/intel-deep-learning-essentials-2025.3.3.18_offline.exe
+ WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
+ ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
+ ONEAPI_INSTALLER_VERSION: "2025.3.3"
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: Use oneAPI Installation Cache
+ uses: actions/cache@v5
+ id: cache-sycl
+ with:
+ path: ${{ env.ONEAPI_ROOT }}
+ key: oneAPI-${{ env.ONEAPI_INSTALLER_VERSION }}-${{ runner.os }}
+
+ - name: Download & Install oneAPI
+ shell: bash
+ if: steps.cache-sycl.outputs.cache-hit != 'true'
+ run: |
+ scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: windows-latest-sycl
+ variant: ccache
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ # TODO: add ssl support ; we will also need to modify win-build-sycl.bat to accept user-specified args
+
+ - name: Build
+ id: cmake_build
+ run: examples/sycl/win-build-sycl.bat
-DGGML_MUSA=ON
time cmake --build build --config Release -j $(nproc)
- ubuntu-22-sycl:
- runs-on: ubuntu-22.04
-
- continue-on-error: true
-
- steps:
- - uses: actions/checkout@v6
-
- - name: add oneAPI to apt
- shell: bash
- run: |
- cd /tmp
- wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
- sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
- rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
- sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main"
-
- - name: install oneAPI dpcpp compiler
- shell: bash
- run: |
- sudo apt update
- sudo apt install intel-oneapi-compiler-dpcpp-cpp libssl-dev
-
- - name: install oneAPI MKL library
- shell: bash
- run: |
- sudo apt install intel-oneapi-mkl-devel
-
- - name: Clone
- id: checkout
- uses: actions/checkout@v6
-
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: ubuntu-22-sycl
- evict-old-files: 1d
- save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
- - name: Build
- id: cmake_build
- run: |
- source /opt/intel/oneapi/setvars.sh
- cmake -B build \
- -DGGML_SYCL=ON \
- -DCMAKE_C_COMPILER=icx \
- -DCMAKE_CXX_COMPILER=icpx
- time cmake --build build --config Release -j $(nproc)
-
- ubuntu-22-sycl-fp16:
- runs-on: ubuntu-22.04
-
- continue-on-error: true
-
- steps:
- - uses: actions/checkout@v6
-
- - name: add oneAPI to apt
- shell: bash
- run: |
- cd /tmp
- wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
- sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
- rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
- sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main"
-
- - name: install oneAPI dpcpp compiler
- shell: bash
- run: |
- sudo apt update
- sudo apt install intel-oneapi-compiler-dpcpp-cpp libssl-dev ninja-build
-
- - name: install oneAPI MKL library
- shell: bash
- run: |
- sudo apt install intel-oneapi-mkl-devel
-
- - name: Clone
- id: checkout
- uses: actions/checkout@v6
-
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: ubuntu-22-sycl-fp16
- evict-old-files: 1d
- save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
- - name: Build
- id: cmake_build
- run: |
- source /opt/intel/oneapi/setvars.sh
- cmake -B build \
- -G "Ninja" \
- -DCMAKE_BUILD_TYPE=Release \
- -DGGML_SYCL=ON \
- -DCMAKE_C_COMPILER=icx \
- -DCMAKE_CXX_COMPILER=icpx \
- -DGGML_SYCL_F16=ON
- time cmake --build build --config Release -j $(nproc)
windows-latest:
runs-on: windows-2025
cmake --build build --config Release -j %NINJA_JOBS% -t ggml
cmake --build build --config Release
- windows-latest-sycl:
- runs-on: windows-2022
-
- defaults:
- run:
- shell: bash
-
- env:
- WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/24751ead-ddc5-4479-b9e6-f9fe2ff8b9f2/intel-deep-learning-essentials-2025.2.1.25_offline.exe
- WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
- ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
- steps:
- - name: Clone
- id: checkout
- uses: actions/checkout@v6
-
- - name: ccache
- uses: ggml-org/ccache-action@v1.2.21
- with:
- key: windows-latest-sycl
- variant: ccache
- evict-old-files: 1d
- save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
-
- - name: Install
- run: |
- scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
-
- # TODO: add ssl support ; we will also need to modify win-build-sycl.bat to accept user-specified args
-
- - name: Build
- id: cmake_build
- run: examples/sycl/win-build-sycl.bat
windows-latest-hip:
runs-on: windows-2022
shell: bash
env:
- WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/24751ead-ddc5-4479-b9e6-f9fe2ff8b9f2/intel-deep-learning-essentials-2025.2.1.25_offline.exe
+ WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b60765d1-2b85-4e85-86b6-cb0e9563a699/intel-deep-learning-essentials-2025.3.3.18_offline.exe
WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
+ ONEAPI_INSTALLER_VERSION: "2025.3.3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
+ - name: Use oneAPI Installation Cache
+ uses: actions/cache@v5
+ id: cache-sycl
+ with:
+ path: ${{ env.ONEAPI_ROOT }}
+ key: oneAPI-${{ env.ONEAPI_INSTALLER_VERSION }}-${{ runner.os }}
+
+ - name: Download & Install oneAPI
+ shell: bash
+ if: steps.cache-sycl.outputs.cache-hit != 'true'
+ run: |
+ scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
+
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
variant: ccache
evict-old-files: 1d
- - name: Install
- run: |
- scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
-
- name: Build
id: cmake_build
shell: cmd
path: llama-bin-win-sycl-x64.zip
name: llama-bin-win-sycl-x64.zip
+ ubuntu-24-sycl:
+ strategy:
+ matrix:
+ build: [fp32, fp16]
+ include:
+ - build: fp32
+ fp16: OFF
+ - build: fp16
+ fp16: ON
+
+ runs-on: ubuntu-24.04
+
+ env:
+ ONEAPI_ROOT: /opt/intel/oneapi/
+ ONEAPI_INSTALLER_VERSION: "2025.3.3"
+
+ steps:
+ - uses: actions/checkout@v6
+
+ - name: Use oneAPI Installation Cache
+ uses: actions/cache@v5
+ id: cache-sycl
+ with:
+ path: ${{ env.ONEAPI_ROOT }}
+ key: oneAPI-${{ env.ONEAPI_INSTALLER_VERSION }}-${{ runner.os }}
+
+ - name: Download & Install oneAPI
+ shell: bash
+ if: steps.cache-sycl.outputs.cache-hit != 'true'
+ run: |
+ cd /tmp
+ wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh
+ sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept
+
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: ubuntu-24-sycl-${{ matrix.build }}
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Build
+ id: cmake_build
+ run: |
+ source /opt/intel/oneapi/setvars.sh
+ cmake -B build \
+ -G "Ninja" \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DGGML_SYCL=ON \
+ -DCMAKE_C_COMPILER=icx \
+ -DCMAKE_CXX_COMPILER=icpx \
+ -DLLAMA_OPENSSL=OFF \
+ -DGGML_NATIVE=OFF \
+ -DGGML_SYCL_F16=${{ matrix.fp16 }}
+ time cmake --build build --config Release -j $(nproc)
+
+ - name: Determine tag name
+ id: tag
+ uses: ./.github/actions/get-tag-name
+
+ - name: Pack artifacts
+ id: pack_artifacts
+ run: |
+ cp LICENSE ./build/bin/
+ tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-${{ matrix.build }}-x64.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
+
+ - name: Upload artifacts
+ uses: actions/upload-artifact@v6
+ with:
+ path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-${{ matrix.build }}-x64.tar.gz
+ name: llama-bin-ubuntu-sycl-${{ matrix.build }}-x64.tar.gz
+
ubuntu-22-rocm:
runs-on: ubuntu-22.04
- ubuntu-cpu
- ubuntu-vulkan
- ubuntu-24-openvino
+ - ubuntu-24-sycl
- android-arm64
- macOS-cpu
- ios-xcode-build
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-${{ needs.ubuntu-24-openvino.outputs.openvino_version }}-x64.tar.gz)
+ - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp32-x64.tar.gz)
+ - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp16-x64.tar.gz)
**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz)
## Recommended Release
+### Windows
+
The following releases are verified and recommended:
|Commit ID|Tag|Release|Verified Platform| Update date|
|3bcd40b3c593d14261fb2abfabad3c0fb5b9e318|b4040 |[llama-b4040-bin-win-sycl-x64.zip](https://github.com/ggml-org/llama.cpp/releases/download/b4040/llama-b4040-bin-win-sycl-x64.zip) |Arc A770/Linux/oneAPI 2024.1<br>MTL Arc GPU/Windows 11/oneAPI 2024.1| 2024-11-19|
|fb76ec31a9914b7761c1727303ab30380fd4f05c|b3038 |[llama-b3038-bin-win-sycl-x64.zip](https://github.com/ggml-org/llama.cpp/releases/download/b3038/llama-b3038-bin-win-sycl-x64.zip) |Arc A770/Linux/oneAPI 2024.1<br>MTL Arc GPU/Windows 11/oneAPI 2024.1||
+### Ubuntu 24.04
+
+The release packages for Ubuntu 24.04 x64 (FP32/FP16) only include the binary files of the llama.cpp SYCL backend. They require the target machine to have pre-installed Intel GPU drivers and oneAPI packages that are the same version as the build package. To get the version and installation info, refer to release.yml: ubuntu-24-sycl -> Download & Install oneAPI.
+
+It is recommended to use them with Intel Docker.
+
+The packages for FP32 and FP16 would have different accuracy and performance on LLMs. Please choose it acording to the test result.
## News
|Verified release|
|-|
+|2025.3.3 |
|2025.2.1|
|2025.1|
|2024.1|
overview / pkg / ggml / sources / llama.cpp / commitdiff