Merge branch 'main' into zhiyul/fix/p2p-dealloc-race

Author: ZhiyuLi-Nvidia

.claude/skills/build-and-test/SKILL.md

@@ -0,0 +1 @@
+See CLAUDE.md for all repository guidelines.

.cursorrules

@@ -75,16 +75,12 @@ runs:
       shell: bash
       run: sudo chown -R $(whoami) /home/runner/
 
-    - name: Setup python
-      uses: actions/setup-python@v5
-      with:
-        python-version: 3.12
-
-    - name: Install uuidgen
+    - name: Setup python and install dependencies
       shell: bash -x -e -u -o pipefail {0}
       run: |
         apt-get update
-        apt-get install -y uuid-runtime
+        apt-get install -y python3.12 python3.12-venv uuid-runtime
+        curl -LsSf https://astral.sh/uv/install.sh | UV_INSTALL_DIR=/usr/local/bin sh
 
     - name: Create run-script (unit test)
       shell: bash -x -e -u -o pipefail {0}
@@ -97,7 +93,6 @@ runs:
         export PYTHONPATH=$(pwd)
         export NEMORUN_HOME=$(pwd)
         export NCCL_DEBUG=INFO
-        pip install --no-cache-dir "uv<0.9.29"
         uv venv .venv
         uv cache clean
         uv sync --no-cache --only-group test
@@ -137,7 +132,6 @@ runs:
 
         export PYTHONPATH=$(pwd)
         export NEMORUN_HOME=$(pwd)
-        pip install --no-cache-dir "uv<0.9.29"
         uv venv .venv
         uv cache clean
         uv sync --no-cache --only-group test

.github/actions/action.yml

@@ -1,4 +1,4 @@
 enabled: true
 auto_sync_draft: false
 auto_sync_ready: true
-trustees_override: ["AAnoosheh", "ArEsKay3", "Autumn1998", "BestJuly", "BoxiangW", "CarlosGomes98", "ChenhanYu", "FDecaYed", "HaochenYuan", "ISEEKYAN", "JRD971000", "Phlip79", "QiZhangNV", "RPrenger", "ShriyaRishab", "Victarry", "Wohox", "ZhiyuLi-Nvidia", "ahmadki", "aklife97", "ananthsub", "asolergi-nv", "buptzyb", "chtruong814", "cjld", "cspades", "cuichenx", "deepakn94", "dimapihtar", "dingqingy-nv", "duncanriach", "erhoo82", "ericharper", "fanshiqing", "faradawn", "frsun-nvda", "gautham-kollu", "gdengk", "guyueh1", "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", "mkhona-nvidia", "nanz-nv", "parthmannan", "prajwal1210", "pthombre", "rhewett-nv", "rogerwaleffe", "sajadn", "sanandaraj5597", "sancha", "santhnm2", "sbak5", "shanmugamr1992", "sharathts", "shengf-nv", "shifangx", "shjwudp", "sidsingh-nvidia", "skyw", "sudhakarsingh27", "tdene", "theothermike", "thomasdhc", "tomlifu", "trintamaki", "tylerpoon", "wdykas", "wplf", "xiaoyao0115", "xuwchen", "yanring", "yaox12", "yaoyu-33", "yashaswikarnati", "yeyu-nvidia", "yobibyte", "youngeunkwon0405", "yueshen2016", "yuzhongw-nvidia", "zhongbozhu"]
+trustees_override: ["AAnoosheh", "ArEsKay3", "Autumn1998", "BestJuly", "BoxiangW", "CarlosGomes98", "ChenhanYu", "FDecaYed", "HaochenYuan", "ISEEKYAN", "JRD971000", "Phlip79", "QiZhangNV", "RPrenger", "ShriyaRishab", "Victarry", "WanZzzzzz", "Wohox", "ZhiyuLi-Nvidia", "ahmadki", "aklife97", "ananthsub", "asolergi-nv", "buptzyb", "chtruong814", "cjld", "cspades", "cuichenx", "deepakn94", "dimapihtar", "dingqingy-nv", "duncanriach", "erhoo82", "ericharper", "fanshiqing", "faradawn", "frsun-nvda", "gautham-kollu", "gdengk", "guyueh1", "hexinw-nvidia", "huvunvidia", "hxbai", "ilml", "jalbericiola", "janEbert", "jaredcasper", "jenchen13", "jiemingz", "jingqiny-99", "jkamalu", "jon-barker", "jstjohn", "kajalj22", "kanz-nv", "keshavb96", "kevalmorabia97", "ko3n1g", "ksivaman", "kunlunl", "kvareddy", "kwyss-nvidia", "layalir", "lhb8125", "lmcafee-nvidia", "maanug-nv", "mathemakitten", "matthieule", "mchrzanowski", "mehraakash", "mkhona-nvidia", "nanz-nv", "parthmannan", "prajwal1210", "pthombre", "rhewett-nv", "rogerwaleffe", "sajadn", "sanandaraj5597", "sancha", "santhnm2", "sbak5", "shanmugamr1992", "sharathts", "sheliang-nv", "shengf-nv", "shifangx", "shjwudp", "sidsingh-nvidia", "skyw", "sudhakarsingh27", "tdene", "theothermike", "thomasdhc", "tomlifu", "trintamaki", "tylerpoon", "wdykas", "wplf", "xiaoyao0115", "xuwchen", "yanring", "yaox12", "yaoyu-33", "yashaswikarnati", "yeyu-nvidia", "yobibyte", "youngeunkwon0405", "yueshen2016", "yuzhongw-nvidia", "zhongbozhu"]

.github/copy-pr-bot.yaml

@@ -1,8 +1,4 @@
 [
-    {
-        "user": "janEbert",
-        "date": "2026-03-25"
-    },
     {
         "user": "gautham-kollu",
         "date": "2026-04-01"
@@ -20,31 +16,47 @@
         "date": "2026-04-22"
     },
     {
-        "user": "BoxiangW",
+        "user": "maanug-nv",
         "date": "2026-04-29"
     },
     {
-        "user": "maanug-nv",
+        "user": "dimapihtar",
         "date": "2026-05-06"
     },
     {
-        "user": "dimapihtar",
+        "user": "gautham-kollu",
         "date": "2026-05-13"
     },
     {
-        "user": "gautham-kollu",
+        "user": "janEbert",
         "date": "2026-05-20"
     },
     {
         "user": "ilml",
         "date": "2026-05-27"
     },
     {
-        "user": "janEbert",
+        "user": "Phlip79",
         "date": "2026-06-03"
     },
     {
-        "user": "maanug-nv",
+        "user": "asolergi-nv",
         "date": "2026-06-10"
+    },
+    {
+        "user": "maanug-nv",
+        "date": "2026-06-17"
+    },
+    {
+        "user": "dimapihtar",
+        "date": "2026-06-24"
+    },
+    {
+        "user": "gautham-kollu",
+        "date": "2026-07-01"
+    },
+    {
+        "user": "janEbert",
+        "date": "2026-07-08"
     }
 ]

.github/oncall_schedule.json

@@ -71,10 +71,10 @@ jobs:
           pushd $BUILD_DIR
             rm LICENSE || true
             docker run --rm -v $(pwd):/workspace -w /workspace $IMAGE bash -c '\
-              for python_version in cp310 cp311 cp312 cp313; do \
+              for python_version in cp311 cp312 cp313; do \
                 /opt/python/${python_version}-${python_version}/bin/pip install --upgrade "setuptools<80.0.0,>=77.0.0" build; \
               done && \
-              for python_version in cp310 cp311 cp312 cp313; do \
+              for python_version in cp311 cp312 cp313; do \
                 /opt/python/${python_version}-${python_version}/bin/python -m build; \
               done \
             '
@@ -118,22 +118,20 @@ jobs:
 
           if [ "$PACKAGE" = "megatron-core" ]; then
             if [[ "$PLATFORM" == "arm64" ]]; then
-              for file in dist/$WHEEL_PREFIX*cp310*aarch64.whl; do
-                pip install --no-cache-dir "$file"
-              done
+              WHEEL_GLOB="dist/${WHEEL_PREFIX}*cp312*aarch64.whl"
             else
-              for file in dist/$WHEEL_PREFIX*cp310*x86_64.whl; do
-                pip install --no-cache-dir "$file"
-              done
+              WHEEL_GLOB="dist/${WHEEL_PREFIX}*cp312*x86_64.whl"
             fi
           else
-            pip install --no-cache-dir dist/$WHEEL_PREFIX*.whl
+            WHEEL_GLOB="dist/${WHEEL_PREFIX}*.whl"
           fi
 
-          sudo rm -rf megatron/
-
-          RELEASE_NUMBER=$(python -c "import $ROOTPATH; print($ROOTPATH.__version__)")
-          test "${{ steps.build-wheel.outputs.expected-release-number }}" == "$RELEASE_NUMBER"
+          docker run --rm -v $(pwd):/workspace -w /workspace $IMAGE bash -c "\
+            /opt/python/cp312-cp312/bin/pip install --no-cache-dir $WHEEL_GLOB && \
+            rm -rf megatron/ && \
+            RELEASE_NUMBER=\$(/opt/python/cp312-cp312/bin/python -c 'import $ROOTPATH; print($ROOTPATH.__version__)') && \
+            test '${{ steps.build-wheel.outputs.expected-release-number }}' == \"\$RELEASE_NUMBER\" \
+          "
 
       - name: Upload wheels
         uses: actions/upload-artifact@v6

.github/workflows/_build_test_publish_wheel.yml

@@ -33,6 +33,12 @@ jobs:
           fetch-depth: 1
           ref: ${{ steps.get-pr-head-commit.outputs.sha }}
 
+      - name: React to trigger comment
+        run: |
+          gh api repos/$REPO/issues/comments/${{ github.event.comment.id }}/reactions \
+            --method POST \
+            -f content='eyes'
+
       - name: Run Claude Code Review
         uses: anthropics/claude-code-action@v1
         with:
@@ -52,6 +58,8 @@ jobs:
             - Critical bugs or logic errors
             - Typos in code, comments, or strings
             - Missing or insufficient test coverage for changed code
+              - If the PR adds a new feature or significant functionality without corresponding tests, suggest adding tests
+              - If the PR fixes a bug that was not caught by an existing unit test, suggest adding a regression test to prevent recurrence
             - Outdated or inaccurate documentation affected by the changes
 
             Do NOT comment on:

.github/workflows/claude_review.yml

@@ -34,13 +34,16 @@ on:
         default: true
 jobs:
   code-freeze:
-    uses: NVIDIA-NeMo/FW-CI-templates/.github/workflows/_code_freeze.yml@v0.22.5
+    uses: NVIDIA-NeMo/FW-CI-templates/.github/workflows/_code_freeze.yml@v0.86.0
     with:
-      library-name: Megatron-Bridge
-      python-package: megatron.bridge
+      library-name: Megatron-Core
+      python-package: megatron.core
       release-type: ${{ inputs.release-type }}
       freeze-commit: ${{ inputs.freeze-commit }}
       dry-run: ${{ inputs.dry-run }}
+      release-branch-prefix: core_
+      use-pat: true
     secrets:
-      SLACK_WEBHOOK: ${{ secrets.SLACK_MAIN_CHANNEL_WEBHOOK }}
+      SLACK_WEBHOOK: ${{ inputs.dry-run && secrets.SLACK_CI_CHANNEL_WEBHOOK ||secrets.SLACK_MAIN_CHANNEL_WEBHOOK }}
       SLACK_WEBHOOK_ADMIN: ${{ secrets.SLACK_TEAM_GROUP_ID }}
+      PAT: ${{ secrets.PAT }}

.github/workflows/release-freeze.yml

@@ -0,0 +1 @@
+See [CLAUDE.md](CLAUDE.md) for all repository guidelines.

AGENTS.md

@@ -0,0 +1,13 @@
+# Repository Guidelines
+
+## Contributing
+
+### Pull Requests
+
+- All PRs must be created as **drafts**. Use `gh pr create --draft` or the GitHub UI draft option.
+- Never push branches directly to `https://github.com/NVIDIA/Megatron-LM`. You must push your branch to a personal fork (e.g. `https://github.com/<your-username>/Megatron-LM`), then open a PR from the fork's branch against `NVIDIA/Megatron-LM`.
+- Read [docs/developer/contribute.md](docs/developer/contribute.md) for the full contribution policy, including code style, commit message conventions, and issue guidelines.
+
+### Code Quality
+
+- After editing imports in any Python files, always run `uv run isort` on those files to fix import order before committing.