LLM inference in C/C++
C++ ggml
[SYCL] Fix CI build & release for SYCL backend (#24387)
Neo Zhang099ea76fb47d
diff --git a/.github/workflows/build-sycl.yml b/.github/workflows/build-sycl.ymlindex ef377c8186..deb0e5479a 100644--- a/.github/workflows/build-sycl.yml+++ b/.github/workflows/build-sycl.yml@@ -34,129 +34,108 @@ env:LLAMA_ARG_LOG_TIMESTAMPS: 1jobs:+ ubuntu-24-sycl:+ strategy:+ matrix:+ build: [fp32, fp16]+ include:+ - build: fp32+ fp16: OFF+ - build: fp16+ fp16: ON-# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23705)-# in order to enable it again, we have to provision dedicated runners to run it-# ubuntu-24-sycl:-# strategy:-# matrix:-# build: [fp32]-# include:-# - build: fp32-# fp16: OFF-#-# runs-on: ubuntu-24.04-#-# env:-# ONEAPI_ROOT: /opt/intel/oneapi/-# ONEAPI_INSTALLER_VERSION: "2025.3.3"-# LEVEL_ZERO_VERSION: "1.28.2"-# LEVEL_ZERO_UBUNTU_VERSION: "u24.04"-#-# continue-on-error: true-#-# steps:-# - uses: actions/checkout@v6-#-# - name: Use oneAPI Installation Cache-# uses: actions/cache@v5-# id: cache-sycl-# with:-# path: ${{ env.ONEAPI_ROOT }}-# key: cache-gha-oneAPI-${{ env.ONEAPI_INSTALLER_VERSION }}-${{ runner.os }}-#-# - name: Download & Install oneAPI-# shell: bash-# if: steps.cache-sycl.outputs.cache-hit != 'true'-# run: |-# cd /tmp-# wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh-# sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept-#-# - name: Install Level Zero SDK-# shell: bash-# run: |-# cd /tmp-# wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb-# wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb-# sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb-#-# - name: Clone-# id: checkout-# uses: actions/checkout@v6-#-# - name: ccache-# uses: ggml-org/[email protected]-# with:-# key: sycl-ubuntu-24-${{ 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)--# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23705)-# in order to enable it again, we have to provision dedicated runners to run it-# 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-# LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero-win-sdk-1.28.2.zip-# 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: ${{ env.ONEAPI_ROOT }}-# key: cache-gha-oneAPI-${{ 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 $WINDOWS_DPCPP_MKL-#-# - name: Install Level Zero SDK-# shell: pwsh-# run: |-# Invoke-WebRequest -Uri "${{ env.LEVEL_ZERO_SDK_URL }}" -OutFile "level-zero-win-sdk.zip"-# Expand-Archive -Path "level-zero-win-sdk.zip" -DestinationPath "C:/level-zero-sdk" -Force-# "LEVEL_ZERO_V1_SDK_PATH=C:/level-zero-sdk" | Out-File -FilePath $env:GITHUB_ENV -Append-#-# - name: ccache-# uses: ggml-org/[email protected]-# with:-# key: sycl-windows-latest-# variant: ccache-# evict-old-files: 1d-# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}-#-# # TODO: add ssl support ; we will also need to modify win-build-sycl.bat to accept user-specified args-#-# - name: Build-# id: cmake_build-# run: examples/sycl/win-build-sycl.bat+ runs-on: ubuntu-24.04++ env:+ ONEAPI_ROOT: /opt/intel/oneapi/+ ONEAPI_INSTALLER_VERSION: "2025.3.3"+ LEVEL_ZERO_VERSION: "1.28.2"+ LEVEL_ZERO_UBUNTU_VERSION: "u24.04"++ continue-on-error: true++ steps:+ - name: Clone+ id: checkout+ uses: actions/checkout@v6++ - name: Download & Install oneAPI+ shell: bash+ run: |+ cd /tmp+ wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh+ sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept++ - name: Install Level Zero SDK+ shell: bash+ run: |+ cd /tmp+ wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb+ wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb+ sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb++ - name: ccache+ uses: ggml-org/[email protected]+ with:+ key: sycl-ubuntu-24-${{ 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+ LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero-win-sdk-1.28.2.zip+ ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"+ ONEAPI_INSTALLER_VERSION: "2025.3.3"+ steps:+ - name: Clone+ id: checkout+ uses: actions/checkout@v6++ - name: Download & Install oneAPI+ shell: bash+ run: |+ scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL++ - name: Install Level Zero SDK+ shell: pwsh+ run: |+ Invoke-WebRequest -Uri "${{ env.LEVEL_ZERO_SDK_URL }}" -OutFile "level-zero-win-sdk.zip"+ Expand-Archive -Path "level-zero-win-sdk.zip" -DestinationPath "C:/level-zero-sdk" -Force+ "LEVEL_ZERO_V1_SDK_PATH=C:/level-zero-sdk" | Out-File -FilePath $env:GITHUB_ENV -Append++ - name: ccache+ uses: ggml-org/[email protected]+ with:+ key: sycl-windows-latest+ variant: ccache+ evict-old-files: 1d+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}++ # TODO: add ssl support ; we will also need to modify win-build-sycl.bat to accept user-specified args++ - name: Build+ id: cmake_build+ run: examples/sycl/win-build-sycl.batdiff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex b656900e5f..efd9ceef4d 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -754,210 +754,202 @@ jobs:path: cudart-llama-bin-win-cuda-${{ matrix.cuda }}-x64.zipname: cudart-llama-bin-win-cuda-${{ matrix.cuda }}-x64.zip-# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23705)-# in order to enable it again, we have to provision dedicated runners to run it-# windows-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-# LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero-win-sdk-1.28.2.zip-# 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: ${{ env.ONEAPI_ROOT }}-# key: cache-gha-oneAPI-${{ 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 $WINDOWS_DPCPP_MKL-#-# - name: Install Level Zero SDK-# shell: pwsh-# run: |-# Invoke-WebRequest -Uri "${{ env.LEVEL_ZERO_SDK_URL }}" -OutFile "level-zero-win-sdk.zip"-# Expand-Archive -Path "level-zero-win-sdk.zip" -DestinationPath "C:/level-zero-sdk" -Force-# "LEVEL_ZERO_V1_SDK_PATH=C:/level-zero-sdk" | Out-File -FilePath $env:GITHUB_ENV -Append-#-# - name: Setup Node.js-# uses: actions/setup-node@v6-# with:-# node-version: "24"-# cache: "npm"-# cache-dependency-path: "tools/ui/package-lock.json"-#-# - name: ccache-# uses: ggml-org/[email protected]-# with:-# key: release-windows-2022-x64-sycl-#-# - name: Build-# id: cmake_build-# shell: cmd-# run: |-# call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force-# cmake -G "Ninja" -B build ^-# -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx ^-# -DCMAKE_BUILD_TYPE=Release ^-# -DGGML_BACKEND_DL=ON -DBUILD_SHARED_LIBS=ON ^-# -DGGML_CPU=OFF -DGGML_SYCL=ON ^-# -DLLAMA_BUILD_BORINGSSL=ON-# cmake --build build --target ggml-sycl -j-#-# - name: Build the release package-# id: pack_artifacts-# run: |-# echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin"-#-# cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin-#-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero_v2.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin-# ZE_LOADER_DLL=$(find "${{ env.ONEAPI_ROOT }}" "$LEVEL_ZERO_V1_SDK_PATH" -iname ze_loader.dll -print -quit 2>/dev/null || true)-# if [ -n "$ZE_LOADER_DLL" ]; then-# echo "Using Level Zero loader: $ZE_LOADER_DLL"-# cp "$ZE_LOADER_DLL" ./build/bin-# else-# echo "Level Zero loader DLL not found in oneAPI or SDK; relying on system driver/runtime"-# fi-#-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl-ls.exe" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libsycl-fallback-bfloat16.spv" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libsycl-native-bfloat16.spv" ./build/bin-#-# cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin-#-# cp "${{ env.ONEAPI_ROOT }}/tcm/latest/bin/tcm.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/tcm/latest/bin/libhwloc-15.dll" ./build/bin-# cp "${{ env.ONEAPI_ROOT }}/umf/latest/bin/umf.dll" ./build/bin-#-# echo "cp oneAPI running time dll files to ./build/bin done"-# 7z a -snl llama-bin-win-sycl-x64.zip ./build/bin/*-#-# - name: Upload the release package-# uses: actions/upload-artifact@v6-# with:-# path: llama-bin-win-sycl-x64.zip-# name: llama-bin-win-sycl-x64.zip+ windows-sycl:-# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23705)-# in order to enable it again, we have to provision dedicated runners to run it-# ubuntu-24-sycl:-#-# strategy:-# matrix:-# build: [fp32]-# include:-# - build: fp32-# fp16: OFF-#-# runs-on: ubuntu-24.04-#-# env:-# ONEAPI_ROOT: /opt/intel/oneapi/-# ONEAPI_INSTALLER_VERSION: "2025.3.3"-# LEVEL_ZERO_VERSION: "1.28.2"-# LEVEL_ZERO_UBUNTU_VERSION: "u24.04"-#-# steps:-# - name: Clone-# id: checkout-# uses: actions/checkout@v6-# with:-# fetch-depth: 0-#-# - name: Use oneAPI Installation Cache-# uses: actions/cache@v5-# id: cache-sycl-# with:-# path: ${{ env.ONEAPI_ROOT }}-# key: cache-gha-oneAPI-${{ env.ONEAPI_INSTALLER_VERSION }}-${{ runner.os }}-#-# - name: Download & Install oneAPI-# shell: bash-# if: steps.cache-sycl.outputs.cache-hit != 'true'-# run: |-# cd /tmp-# wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh-# sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept-#-# - name: Install Level Zero SDK-# shell: bash-# run: |-# cd /tmp-# wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb-# wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb-# sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb-#-# - name: Setup Node.js-# uses: actions/setup-node@v6-# with:-# node-version: "24"-# cache: "npm"-# cache-dependency-path: "tools/ui/package-lock.json"-#-# - name: ccache-# uses: ggml-org/[email protected]-# with:-# key: release-ubuntu-24.04-sycl-#-# - name: Build-# id: cmake_build-# run: |-# source /opt/intel/oneapi/setvars.sh-# cmake -B build \-# -G "Ninja" \-# -DCMAKE_BUILD_TYPE=Release \-# -DGGML_SYCL=ON \-# -DCMAKE_C_COMPILER=icx \-# -DCMAKE_CXX_COMPILER=icpx \-# -DLLAMA_OPENSSL=OFF \-# -DGGML_NATIVE=OFF \-# -DGGML_SYCL_F16=${{ 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+ 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+ LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero-win-sdk-1.28.2.zip+ ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"+ ONEAPI_INSTALLER_VERSION: "2025.3.3"++ steps:+ - name: Clone+ id: checkout+ uses: actions/checkout@v6++ - name: Download & Install oneAPI+ shell: bash+ run: |+ scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL++ - name: Install Level Zero SDK+ shell: pwsh+ run: |+ Invoke-WebRequest -Uri "${{ env.LEVEL_ZERO_SDK_URL }}" -OutFile "level-zero-win-sdk.zip"+ Expand-Archive -Path "level-zero-win-sdk.zip" -DestinationPath "C:/level-zero-sdk" -Force+ "LEVEL_ZERO_V1_SDK_PATH=C:/level-zero-sdk" | Out-File -FilePath $env:GITHUB_ENV -Append++ - name: Setup Node.js+ uses: actions/setup-node@v6+ with:+ node-version: "24"+ cache: "npm"+ cache-dependency-path: "tools/ui/package-lock.json"++ - name: ccache+ uses: ggml-org/[email protected]+ with:+ key: release-windows-2022-x64-sycl++ - name: Build+ id: cmake_build+ shell: cmd+ run: |+ call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force+ cmake -G "Ninja" -B build ^+ -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx ^+ -DCMAKE_BUILD_TYPE=Release ^+ -DGGML_BACKEND_DL=ON -DBUILD_SHARED_LIBS=ON ^+ -DGGML_CPU=OFF -DGGML_SYCL=ON ^+ -DLLAMA_BUILD_BORINGSSL=ON+ cmake --build build --target ggml-sycl -j %NUMBER_OF_PROCESSORS%++ - name: ccache-clear+ uses: ./.github/actions/ccache-clear+ with:+ key: release-windows-2022-x64-sycl++ - name: Build the release package+ id: pack_artifacts+ run: |+ echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin"++ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin++ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero_v2.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin+ ZE_LOADER_DLL=$(find "${{ env.ONEAPI_ROOT }}" "$LEVEL_ZERO_V1_SDK_PATH" -iname ze_loader.dll -print -quit 2>/dev/null || true)+ if [ -n "$ZE_LOADER_DLL" ]; then+ echo "Using Level Zero loader: $ZE_LOADER_DLL"+ cp "$ZE_LOADER_DLL" ./build/bin+ else+ echo "Level Zero loader DLL not found in oneAPI or SDK; relying on system driver/runtime"+ fi++ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl-ls.exe" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libsycl-fallback-bfloat16.spv" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libsycl-native-bfloat16.spv" ./build/bin++ cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin++ cp "${{ env.ONEAPI_ROOT }}/tcm/latest/bin/tcm.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/tcm/latest/bin/libhwloc-15.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/umf/latest/bin/umf.dll" ./build/bin++ echo "cp oneAPI running time dll files to ./build/bin done"+ 7z a -snl llama-bin-win-sycl-x64.zip ./build/bin/*++ - name: Upload the release package+ uses: actions/upload-artifact@v6+ with:+ 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"+ LEVEL_ZERO_VERSION: "1.28.2"+ LEVEL_ZERO_UBUNTU_VERSION: "u24.04"++ steps:+ - name: Clone+ id: checkout+ uses: actions/checkout@v6+ with:+ fetch-depth: 0++ - name: Download & Install oneAPI+ shell: bash+ 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: Install Level Zero SDK+ shell: bash+ run: |+ cd /tmp+ wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb+ wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb+ sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb++ - name: Setup Node.js+ uses: actions/setup-node@v6+ with:+ node-version: "24"+ cache: "npm"+ cache-dependency-path: "tools/ui/package-lock.json"++ - name: ccache+ uses: ggml-org/[email protected]+ with:+ key: release-ubuntu-24.04-sycl-${{ matrix.build }}++ - name: Build+ id: cmake_build+ run: |+ source /opt/intel/oneapi/setvars.sh+ cmake -B build \+ -G "Ninja" \+ -DCMAKE_BUILD_TYPE=Release \+ -DGGML_SYCL=ON \+ -DCMAKE_C_COMPILER=icx \+ -DCMAKE_CXX_COMPILER=icpx \+ -DLLAMA_OPENSSL=OFF \+ -DGGML_NATIVE=OFF \+ -DGGML_SYCL_F16=${{ matrix.fp16 }}+ time cmake --build build --config Release -j $(nproc)++ - name: ccache-clear+ uses: ./.github/actions/ccache-clear+ with:+ key: release-ubuntu-24.04-sycl-${{ matrix.build }}++ - 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.gzubuntu-22-rocm:needs: [check-release]