LLM inference in C/C++
C++ ggml
ci : update the oneAPI toolkit to 2026.1 (#29273)
Asahi-Prvfc07d781e61f
diff --git a/.devops/intel.Dockerfile b/.devops/intel.Dockerfileindex b4bcd94b92..db46fd868d 100644--- a/.devops/intel.Dockerfile+++ b/.devops/intel.Dockerfile@@ -1,4 +1,4 @@-ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04+ARG ONEAPI_VERSION=2026.1.1-devel-ubuntu24.04ARG BUILD_DATE=N/AARG APP_VERSION=N/AARG APP_REVISION=N/A@@ -19,7 +19,7 @@ RUN npm ciCOPY tools/ui/ ./RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build-FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS build+FROM docker.io/intel/oneapi-toolkit:$ONEAPI_VERSION AS buildARG GGML_SYCL_F16=ONARG LEVEL_ZERO_VERSION=1.28.2@@ -59,7 +59,7 @@ RUN mkdir -p /app/full \&& cp requirements.txt /app/full \&& cp .devops/tools.sh /app/full/tools.sh-FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS base+FROM docker.io/intel/oneapi-toolkit:$ONEAPI_VERSION AS baseARG BUILD_DATE=N/AARG APP_VERSION=N/Adiff --git a/.github/workflows/build-sycl.yml b/.github/workflows/build-sycl.ymlindex 5424a8607e..ddc4e7f2b1 100644--- a/.github/workflows/build-sycl.yml+++ b/.github/workflows/build-sycl.yml@@ -48,7 +48,7 @@ jobs:env:ONEAPI_ROOT: /opt/intel/oneapi/- ONEAPI_INSTALLER_VERSION: "2025.3.3"+ ONEAPI_INSTALLER_VERSION: "2026.1"LEVEL_ZERO_VERSION: "1.33.1"LEVEL_ZERO_UBUNTU_VERSION: "u24.04"@@ -63,8 +63,8 @@ jobs:shell: bashrun: |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+ wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/5996e26b-f48a-42b1-8db0-b002ad0bd8d7/intel-oneapi-toolkit-2026.1.1.33_offline.sh -O intel-oneapi-toolkit_offline.sh+ sudo bash intel-oneapi-toolkit_offline.sh -s -a --silent --eula accept- name: Install Level Zero SDKshell: bash@@ -129,11 +129,11 @@ jobs:shell: bashenv:- 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_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/0cb67a0d-67f6-410b-868b-f4a0a17ff0cf/intel-oneapi-toolkit-2026.1.1.32_offline.exeWINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.develLEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.33.1/level-zero-win-sdk-1.33.1.zipONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"- ONEAPI_INSTALLER_VERSION: "2025.3.3"+ ONEAPI_INSTALLER_VERSION: "2026.1"steps:- name: Cloneid: checkoutdiff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex be13d9118a..b5dba37de8 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -1344,11 +1344,11 @@ jobs:shell: bashenv:- 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_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/0cb67a0d-67f6-410b-868b-f4a0a17ff0cf/intel-oneapi-toolkit-2026.1.1.32_offline.exeWINDOWS_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+ LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.33.1/level-zero-win-sdk-1.33.1.zipONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"- ONEAPI_INSTALLER_VERSION: "2025.3.3"+ ONEAPI_INSTALLER_VERSION: "2026.1"steps:- name: Clone@@ -1391,9 +1391,11 @@ jobs: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 "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.6.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.3.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_def.3.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_avx2.3.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.3.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero_v2.dll" ./build/bin@@ -1408,13 +1410,11 @@ jobs:echo "Level Zero loader DLL not found in oneAPI or SDK; relying on system driver/runtime"fi- cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin+ cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl9.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl-ls.exe" ./build/bin- cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libsycl-fallback-bfloat16.spv" ./build/bin- cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libsycl-native-bfloat16.spv" ./build/bincp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bincp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin@@ -1454,8 +1454,8 @@ jobs:env:ONEAPI_ROOT: /opt/intel/oneapi/- ONEAPI_INSTALLER_VERSION: "2025.3.3"- LEVEL_ZERO_VERSION: "1.28.2"+ ONEAPI_INSTALLER_VERSION: "2026.1"+ LEVEL_ZERO_VERSION: "1.33.1"LEVEL_ZERO_UBUNTU_VERSION: "u24.04"steps:@@ -1469,16 +1469,16 @@ jobs:shell: bashrun: |cd /tmp- wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh- sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept+ wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/5996e26b-f48a-42b1-8db0-b002ad0bd8d7/intel-oneapi-toolkit-2026.1.1.33_offline.sh -O intel-oneapi-toolkit_offline.sh+ sudo bash intel-oneapi-toolkit_offline.sh -s -a --silent --eula accept- name: Install Level Zero SDKshell: bashrun: |cd /tmp- wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${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${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb- sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb+ wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/libze1_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O libze1.deb+ wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/libze-dev_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O libze-dev.deb+ sudo apt-get install -y ./libze1.deb ./libze-dev.deb- name: Download UI builduses: actions/download-artifact@v7diff --git a/docs/backend/SYCL.md b/docs/backend/SYCL.mdindex f9da1ab3ed..7f2b551829 100644--- a/docs/backend/SYCL.md+++ b/docs/backend/SYCL.md@@ -52,6 +52,10 @@ The packages for FP32 and FP16 would have different accuracy and performance on## News+- 2026.09+ - Update the CI build environment for oneAPI 2026.1 (unified oneAPI Toolkit). oneDNN is removed from the Deep Learning Essentials package in 2026.0, so the CI now uses the oneAPI Toolkit installer which still includes oneDNN.+ - oneAPI 2026.1 improves the SYCL build performance: measured with the same code on Arc B570, prompt processing 1331 vs 434 t/s (3.1x) vs the 2025.3-based release build.+- 2026.04-05- Optimize mul_mat by reorder feature for data type: Q4_K, Q5_K, Q6_K, Q8_0.- Fused MoE.@@ -257,7 +261,7 @@ Platform #0: Intel(R) OpenCL HD Graphics`-- Device #0: Intel(R) Iris(R) Xe Graphics [0x9a49]```-2. **Install Intel® oneAPI Base toolkit**+2. **Install Intel® oneAPI Toolkit**SYCL backend depends on:- Intel® oneAPI DPC++/C++ compiler/running-time.@@ -267,11 +271,11 @@ SYCL backend depends on:- **For Intel GPU**-All above are included in both **Intel® oneAPI Base toolkit** and **Intel® Deep Learning Essentials** packages.+With the 2026.0 release, the Intel® oneAPI Base toolkit and the HPC toolkit are combined into the **Intel® oneAPI Toolkit**, and **oneDNN is removed from the Intel® Deep Learning Essentials** package (oneDNN is distributed separately since then). The **Intel® oneAPI Toolkit** includes oneDNN until 2027.0.-It's recommended to install **Intel® Deep Learning Essentials** which only provides the necessary libraries with less size.+It's recommended to install the **Intel® oneAPI Toolkit**.-The **Intel® oneAPI Base toolkit** and **Intel® Deep Learning Essentials** can be obtained from the official [Intel® oneAPI Base Toolkit](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit.html) page.+The **Intel® oneAPI Toolkit** can be obtained from the official [Intel® oneAPI Toolkit](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html) page.Please follow the instructions for downloading and installing the Toolkit for Linux, and preferably keep the default installation values unchanged, notably the installation path *(`/opt/intel/oneapi` by default)*.@@ -281,6 +285,7 @@ Upon a successful installation, SYCL is enabled for the available Intel devices,|Verified release||-|+|2026.1 ||2025.3.3 ||2025.2.1||2025.1|