Merge branch 'main' into tkuczynski/max_bps_proton

Author: dev-tomek

.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