chore: nightly sync main into dev (27_05_2026)

.github/ISSUE_TEMPLATE/bug_report.md

@@ -9,7 +9,7 @@ assignees: ''
 
 **Describe the bug**
 
-A clear and concise description of what the bug is. Tag the [@mcore-oncall](https://github.com/orgs/NVIDIA/teams/mcore-oncall) 
+A clear and concise description of what the bug is. Tag @NVIDIA/mcore-oncall
 to get oncall's attention to this issue.
 
 **Steps/Code to reproduce bug**
@@ -26,4 +26,4 @@ A clear and concise description of what you expected to happen.
 
 **Additional context**
 
-Add any other context about the problem here. 
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -10,7 +10,7 @@ assignees: ''
 **Is your feature request related to a problem? Please describe.**
 A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
 
-Tag the [@mcore-oncall](https://github.com/orgs/NVIDIA/teams/mcore-oncall) 
+Tag @NVIDIA/mcore-oncall
 to get oncall's attention to this issue.
 
 **Describe the solution you'd like**

.github/ISSUE_TEMPLATE/question.md

@@ -9,5 +9,5 @@ assignees: ''
 ---
 
 **Your question**
-Ask a clear and concise question about Megatron-LM. Tag the [@mcore-oncall](https://github.com/orgs/NVIDIA/teams/mcore-oncall) 
-to get oncall's attention to this issue.
+Ask a clear and concise question about Megatron-LM. Tag @NVIDIA/mcore-oncall
+to get oncall's attention to this issue.

.github/ISSUE_TEMPLATE/regression.md

@@ -8,7 +8,7 @@ assignees: ''
 ---
 
 **Describe the regression**
-A clear and concise description of what the regression is. Tag the [@mcore-oncall](https://github.com/orgs/NVIDIA/teams/mcore-oncall) 
+A clear and concise description of what the regression is. Tag @NVIDIA/mcore-oncall
 to get oncall's attention to this issue.
 
 **To Reproduce**

.github/actions/action.yml

@@ -65,6 +65,10 @@ inputs:
     description: "Trigger cadence for cadence filter (pr|nightly|mergegroup). Empty disables filter."
     required: false
     default: ""
+  sha:
+    description: "Git ref to check out. Must match the SHA used by the upstream parse step so recipes don't diverge between scheduling and execution."
+    required: false
+    default: ""
 runs:
   using: "composite"
   steps:
@@ -74,10 +78,20 @@ runs:
 
     - name: Checkout repository
       uses: actions/checkout@v6
+      with:
+        ref: ${{ inputs.sha }}
 
     - name: Change ownership of /home/runner/
       shell: bash
-      run: sudo chown -R $(whoami) /home/runner/
+      # Tolerate vanishing `.git/objects/pack/.tmp-*` files: the prior
+      # `actions/checkout` may leave a background `git gc --auto` running,
+      # whose `git pack-objects` renames/deletes temp files while `chown`
+      # is walking the tree. On failure, wait 5 s for gc to settle, retry,
+      # then succeed unconditionally.
+      run: |
+        sudo chown -R $(whoami) /home/runner/ 2>/dev/null && exit 0
+        sleep 5
+        sudo chown -R $(whoami) /home/runner/ 2>/dev/null || true
 
     - name: Setup python
       uses: actions/setup-python@v5
@@ -178,6 +192,20 @@ runs:
       id: timeout_in_seconds
       run: echo "main=$(( ${{ inputs.timeout }} * 60 ))" | tee -a "$GITHUB_OUTPUT"
 
+    - name: Prepare AWS Docker config
+      if: ${{ contains(inputs.container-image, '.dkr.ecr.') }}
+      shell: bash -x -e -u -o pipefail {0}
+      run: |
+        mkdir -p "$RUNNER_TEMP/.docker"
+        printf '{}\n' > "$RUNNER_TEMP/.docker/config.json"
+        echo "DOCKER_CONFIG=$RUNNER_TEMP/.docker" | tee -a "$GITHUB_ENV"
+
+    - name: Login to AWS ECR
+      if: ${{ contains(inputs.container-image, '.dkr.ecr.') }}
+      uses: aws-actions/amazon-ecr-login@v2
+      env:
+        AWS_REGION: us-east-1
+
     - name: Pull container
       shell: bash -x -e -u -o pipefail {0}
       run: |
@@ -209,6 +237,8 @@ runs:
       if: always()
       env:
         IS_UNIT_TEST: ${{ inputs.is_unit_test == 'true' }}
+        MAIN_CONCLUSION: ${{ steps.run-main-script.conclusion }}
+        MAIN_EXIT_CODE: ${{ steps.run-main-script.outputs.exit_code }}
       run: |
         logs_report=logs-${{ inputs.test_case }}-${{ github.run_id }}-$(cat /proc/sys/kernel/random/uuid)
         echo "logs_report=$logs_report" | sed 's/\//-/g' | sed 's/\*/-/g' | tee -a "$GITHUB_OUTPUT"
@@ -219,8 +249,12 @@ runs:
         fi
         echo "coverage_report=$coverage_report" | tee -a "$GITHUB_OUTPUT"
 
-        EXIT_CODE=${{ steps.run-main-script.outputs.exit_code }}
-        IS_SUCCESS=$([[ "$EXIT_CODE" -eq 0 ]] && echo "true" || echo "false")
+        EXIT_CODE="${MAIN_EXIT_CODE:-${MAIN_CONCLUSION}}"
+        if [[ "$MAIN_CONCLUSION" == "success" ]]; then
+          IS_SUCCESS=true
+        else
+          IS_SUCCESS=false
+        fi
 
         if [[ "$IS_SUCCESS" == "false" && "${{ inputs.is-optional }}" == "true" ]]; then
           echo "::warning::Test failed but is marked optional — treating as success."

.github/copy-pr-bot.yaml

@@ -1,4 +1,4 @@
 enabled: true
 auto_sync_draft: false
 auto_sync_ready: true
-trustees_override: ["AAnoosheh", "ArEsKay3", "Autumn1998", "BestJuly", "BoxiangW", "CarlosGomes98", "ChenhanYu", "Connor-XY", "FDecaYed", "HaochenYuan", "ISEEKYAN", "JRD971000", "Mellonta", "Phlip79", "QiZhangNV", "RPrenger", "ShriyaRishab", "Victarry", "WanZzzzzz", "Wohox", "YangFei1990", "ZhiyuLi-Nvidia", "ahmadki", "aklife97", "ananthsub", "aroshanghias-nvd", "asolergi-nv", "balasaajay", "buptzyb", "chtruong814", "cjld", "cspades", "cuichenx", "deepakn94", "dimapihtar", "dingqingy-nv", "duncanriach", "erhoo82", "ericharper", "fanshiqing", "faradawn", "fitsumreda", "frsun-nvda", "gautham-kollu", "gdengk", "guihong-nv", "guyueh1", "hexinw-nvidia", "huvunvidia", "hxbai", "ilml", "jalbericiola", "janEbert", "jaredcasper", "jenchen13", "jiemingz", "jingqiny-99", "jkamalu", "jon-barker", "jstjohn", "kajalj22", "kanz-nv", "kevalmorabia97", "ko3n1g", "ksivaman", "kunlunl", "kvareddy", "kwyss-nvidia", "layalir", "lhb8125", "lmcafee-nvidia", "maanug-nv", "mathemakitten", "matthieule", "mchrzanowski", "mehraakash", "minitu", "mkhona-nvidia", "nanz-nv", "ntajbakhsh", "parthmannan", "prajwal1210", "pthombre", "rhewett-nv", "rogerwaleffe", "sajadn", "sanandaraj5597", "sancha", "santhnm2", "sbak5", "shanmugamr1992", "sharathts", "sheliang-nv", "shengf-nv", "shifangx", "shjwudp", "sidsingh-nvidia", "skyw", "sraman-rgb", "sudhakarsingh27", "tdene", "theothermike", "thomasdhc", "tomlifu", "trintamaki", "tylerpoon", "wdykas", "wplf", "wujingyue", "xiaoyao0115", "xuantengh", "xuwchen", "yanring", "yaox12", "yaoyu-33", "yashaswikarnati", "yeyu-nvidia", "yobibyte", "youngeunkwon0405", "yueshen2016", "yuzhongw-nvidia", "zhongbozhu"]
+trustees_override: ["AAnoosheh", "ArEsKay3", "Autumn1998", "BestJuly", "BoxiangW", "CarlosGomes98", "ChenhanYu", "Connor-XY", "FDecaYed", "HaochenYuan", "ISEEKYAN", "JF-D", "JRD971000", "Mellonta", "Phlip79", "QiZhangNV", "RPrenger", "ShriyaRishab", "Victarry", "WanZzzzzz", "Wohox", "YangFei1990", "ZhiyuLi-Nvidia", "adistomar", "ahmadki", "aklife97", "ananthsub", "aroshanghias-nvd", "asolergi-nv", "athitten", "balasaajay", "buptzyb", "chtruong814", "cjld", "cspades", "cuichenx", "deepakn94", "dimapihtar", "dingqingy-nv", "duncanriach", "erhoo82", "ericharper", "fanshiqing", "faradawn", "fitsumreda", "frsun-nvda", "gautham-kollu", "gdengk", "guihong-nv", "guyueh1", "hexinw-nvidia", "huvunvidia", "hxbai", "ilml", "jalbericiola", "janEbert", "jaredcasper", "jenchen13", "jiemingz", "jingqiny-99", "jkamalu", "jon-barker", "jstjohn", "kajalj22", "kevalmorabia97", "ko3n1g", "ksivaman", "kunlunl", "kvareddy", "kwyss-nvidia", "layalir", "lhb8125", "liding-nv", "lmcafee-nvidia", "maanug-nv", "mathemakitten", "matthieule", "mchrzanowski", "mehraakash", "minitu", "mkhona-nvidia", "nanz-nv", "ntajbakhsh", "parthmannan", "prajwal1210", "pthombre", "rapatel", "rhewett-nv", "rogerwaleffe", "sajadn", "sanandaraj5597", "sancha", "santhnm2", "sbak5", "shanmugamr1992", "sharathts", "sheliang-nv", "shengf-nv", "shifangx", "shjwudp", "sidsingh-nvidia", "skyw", "sraman-rgb", "sudhakarsingh27", "tdene", "theothermike", "thomasdhc", "tomlifu", "trintamaki", "tylerpoon", "wdykas", "wplf", "wujingyue", "xiaoyao0115", "xuantengh", "xuwchen", "yaox12", "yaoyu-33", "yashaswikarnati", "yeyu-nvidia", "yobibyte", "youngeunkwon0405", "yueshen2016", "yuzhongw-nvidia", "zhongbozhu"]

.github/oncall_schedule.json

@@ -1,16 +1,4 @@
 [
-    {
-        "user": "janEbert",
-        "date": "2026-05-06"
-    },
-    {
-        "user": "dimapihtar",
-        "date": "2026-05-13"
-    },
-    {
-        "user": "ilml",
-        "date": "2026-05-20"
-    },
     {
         "user": "wujingyue",
         "date": "2026-05-27"
@@ -46,5 +34,17 @@
     {
         "user": "Phlip79",
         "date": "2026-07-22"
+    },
+    {
+        "user": "YangFei1990",
+        "date": "2026-07-29"
+    },
+    {
+        "user": "asolergi-nv",
+        "date": "2026-08-05"
+    },
+    {
+        "user": "dimapihtar",
+        "date": "2026-08-12"
     }
 ]

.github/pull_request_template.md

@@ -1,7 +1,9 @@
+- [ ] I, the PR author, have personally reviewed every line of this PR.
+
 # What does this PR do ?
 <!-- Add a one line overview of what this PR aims to accomplish. -->
 
-:warning: For major changes (either in lines of code or in its impact), please make sure to first share a design doc with the team. If you're unsure what's the best way to do so, contact the @mcore-oncall.
+:warning: For major changes (either in lines of code or in its impact), please make sure to first share a design doc with the team. If you're unsure what's the best way to do so, contact @NVIDIA/mcore-oncall.
 
 ## Issue tracking
 
@@ -24,7 +26,7 @@ Linked issue: <!-- e.g. Fixes #1234 / Related to #1234 -->
 
 ### Code review
 
-Feel free to message or comment the [@mcore-oncall](https://github.com/orgs/NVIDIA/teams/mcore-oncall) to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!
+Feel free to message or comment @NVIDIA/mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!
 
 All PRs start as **draft**. If you open a non-draft PR, it will be automatically converted to draft.
 
@@ -50,10 +52,3 @@ Once all required reviewers have approved, the `Approved` label is applied **aut
 ### Merge
 
 Any member of [mcore-engineers](https://github.com/orgs/NVIDIA/teams/mcore-engineers) will be able to merge your PR.
-
-<details>
-<summary>For MRs into `dev` branch</summary>
-The proposed review process for `dev` branch is under active discussion.
-
-MRs are mergable after one approval by either `eharper@nvidia.com` or `zijiey@nvidia.com`.
-</details>

.github/workflows/_build_test_publish_wheel.yml

@@ -18,7 +18,7 @@ on:
         default: true
     secrets:
       TWINE_PASSWORD:
-        required: true
+        required: false
 
 jobs:
   build-and-test-wheels:
@@ -74,7 +74,7 @@ jobs:
             rm LICENSE || true
             docker run --rm -e NO_VCS_VERSION=1 -v $(pwd):/workspace -w /workspace $IMAGE bash -c '\
               for python_version in cp311 cp312 cp313; do \
-                /opt/python/${python_version}-${python_version}/bin/pip install --upgrade "setuptools<80.0.0,>=77.0.0" build; \
+                /opt/python/${python_version}-${python_version}/bin/pip install --upgrade "setuptools>=80" build; \
               done && \
               for python_version in cp311 cp312 cp313; do \
                 /opt/python/${python_version}-${python_version}/bin/python -m build; \
@@ -144,7 +144,8 @@ jobs:
   publish-wheels:
     needs: [build-and-test-wheels]
     runs-on: ubuntu-latest
-    if: inputs.no-publish == false
+    environment:
+      name: ${{ inputs.no-publish && 'public' || 'main' }}
     strategy:
       fail-fast: false
       matrix:
@@ -171,6 +172,7 @@ jobs:
           TWINE_PASSWORD: ${{ secrets.TWINE_PASSWORD }}
           TWINE_REPOSITORY: ${{ (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/r')) && 'pypi' || 'testpypi' }}
           PLATFORM: ${{ matrix.PLATFORM }}
+          DRY_RUN: ${{ inputs.no-publish }}
         run: |
 
           # Delete sdist for arm64 since we already upload it with amd64.
@@ -180,9 +182,15 @@ jobs:
 
           ls -al dist/
           pip install twine
-          twine upload \
-            --verbose \
-            -r $TWINE_REPOSITORY \
-            -u $TWINE_USERNAME \
-            -p $TWINE_PASSWORD \
-            dist/*
+
+          if [[ "$DRY_RUN" == "false" ]]; then
+            [[ -z "$TWINE_PASSWORD" ]] && { echo "::error::TWINE_PASSWORD unset"; exit 1; }
+            twine upload \
+              --verbose \
+              -r $TWINE_REPOSITORY \
+              -u $TWINE_USERNAME \
+              -p $TWINE_PASSWORD \
+              dist/*
+          else
+            echo "[dry-run] would execute: twine upload --verbose -r $TWINE_REPOSITORY -u <user> -p <pass> dist/*"
+          fi