Merge branch 'main' into mdziado/gluon

Author: mieshkiwrk

.github/WINDOWS.md

@@ -39,7 +39,7 @@ Install Microsoft Visual Studio 2022 and make sure the following [components](ht
 
 ### Intel® Deep Learning Essentials
 
-Install [Intel® Deep Learning Essentials 2025.2.1](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html?packages=dl-essentials&dl-essentials-os=windows&dl-win=offline).
+Install [Intel® Deep Learning Essentials 2025.3.1](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html?packages=dl-essentials&dl-essentials-os=windows&dl-win=offline).
 By default, it is installed to `C:\Program Files (x86)\Intel\oneAPI`.
 
 ### Chocolatey

.github/pins/e2e_reference_torch-xpu-ops.txt

@@ -1 +1 @@
-1e69f40b3c03492eb3dd7e03462a5566f29674d3
+549347d24e9b509b653a350053d56992fc8436ad

.github/pins/pytorch.txt

@@ -1 +1 @@
-01f94d4096060597e2815efe385255ac19c9c787
+365a6c84db516f244b7234b7aa3c8843af52936b

.github/workflows/build-test-reusable.yml

@@ -329,14 +329,6 @@ jobs:
           export PYTEST_MAX_PROCESSES=4
           ${{ env.TRITON_TEST_CMD }} --triton-kernels
 
-      # FIXME: make sure new tutorials are added to one of the groups (scaled_dot, rest, tutorial-faX)
-      - name: Select tutorials to run (scaled_dot)
-        if: matrix.suite == 'scaled_dot'
-        run: |
-          cat <<EOF | tee tutorials.txt
-          09-persistent-matmul
-          EOF
-
       - name: Select tutorials to run (rest)
         if: matrix.suite == 'rest'
         run: |
@@ -348,11 +340,12 @@ jobs:
           05-layer-norm
           07-extern-functions
           08-grouped-gemm
+          09-persistent-matmul
           10-experimental-block-pointer
           EOF
 
       - name: Run Tutorials
-        if: matrix.suite == 'scaled_dot' || matrix.suite == 'rest'
+        if: matrix.suite == 'rest'
         run: |
           ${{ env.TRITON_TEST_CMD }} --select-from-file tutorials.txt --tutorial
 

.github/workflows/pip-test-windows.yml

@@ -90,7 +90,7 @@ jobs:
           .venv\Scripts\activate.ps1
           Invoke-BatchFile "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvarsall.bat" x64
           cd ${{ env.NEW_WORKSPACE }}
-          pip install -U pybind11 'cmake>=3.20,<4.0' intel-sycl-rt==2025.2.1 build
+          pip install -U pybind11 'cmake>=3.20,<4.0' intel-sycl-rt==2025.3.1 build
           # `build` can't determine that Ninja is already installed.
           # similar issue: https://github.com/pypa/build/issues/506
           python -m build --wheel --no-isolation --skip-dependency-check