Merge branch 'master' into loadams/torch19

Author: loadams

.github/ISSUE_TEMPLATE/ci_failure_report.md

@@ -0,0 +1,10 @@
+---
+name: CI failure report
+about: Report a DeepSpeed CI failure
+title: "{{ env.GITHUB_WORKFLOW }} CI test failure"
+labels: ci-failure
+assignees: ''
+
+---
+
+The Nightly CI for {{ env.GITHUB_SERVER_URL }}/{{ env.GITHUB_REPOSITORY }}/actions/runs/{{ env.GITHUB_RUN_ID }} failed.

.github/workflows/amd-mi200.yml

@@ -8,6 +8,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+  issues: write
+
 jobs:
   amd-tests:
     # The type of runner that the job will run on
@@ -65,3 +69,12 @@ jobs:
           cd tests
           pytest $PYTEST_OPTS -n 4 --verbose unit/
           pytest $PYTEST_OPTS -m 'sequential' unit/
+
+      - name: Open GitHub issue if nightly CI fails
+        if: failure()
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true

.github/workflows/nv-h100.yml

@@ -8,6 +8,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+  issues: write
+
 jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, h100]
@@ -49,3 +53,12 @@ jobs:
           cd tests
           python -m pytest $PYTEST_OPTS -n 4  unit/ --torch_ver="2.0" --cuda_ver="12"
           python -m pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.0" --cuda_ver="12"
+
+      - name: Open GitHub issue if nightly CI fails
+        if: failure()
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true

.github/workflows/nv-nightly.yml

@@ -8,6 +8,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+    contents: read
+    issues: write
+
 jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, cu116, v100]
@@ -47,3 +51,12 @@ jobs:
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
           pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="1.13" --cuda_ver="11.6"
+
+      - name: Open GitHub issue if nightly CI fails
+        if: failure()
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true

.github/workflows/nv-torch-nightly-v100.yml

@@ -8,6 +8,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+  issues: write
+
 jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, cu116, v100]
@@ -48,3 +52,12 @@ jobs:
           cd tests
           pytest $PYTEST_OPTS --forked -n 4 unit/
           pytest $PYTEST_OPTS --forked -m 'sequential' unit/
+
+      - name: Open GitHub issue if nightly CI fails
+        if: failure()
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true

.github/workflows/nv-torch19-p40.yml

@@ -12,6 +12,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+    contents: read
+    issues: write
+
 jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, cu111, p40]
@@ -51,3 +55,12 @@ jobs:
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
           pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="1.9" --cuda_ver="11.1"
+
+      - name: Open GitHub issue if nightly CI fails
+        if: failure()
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true

.github/workflows/nv-torch19-v100.yml

@@ -12,6 +12,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+  issues: write
+
 jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, cu111, v100]
@@ -52,3 +56,12 @@ jobs:
           cd tests
           pytest $PYTEST_OPTS --forked -n 4  unit/ --torch_ver="1.9" --cuda_ver="11"
           pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="1.9" --cuda_ver="11"
+
+      - name: Open GitHub issue if nightly CI fails
+        if: failure()
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true