Split merge-main-into-dev: docs and CI changes

.github/actions/action.yml

@@ -59,7 +59,7 @@ runs:
       run: echo "node_name=$NODE_NAME" | tee -a "$GITHUB_OUTPUT"
 
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v6
 
     - name: Change ownership of /home/runner/
       shell: bash
@@ -98,7 +98,8 @@ runs:
           --environment dev \
           --platform dgx_h100 \
           --tag ${{ inputs.tag }} \
-          --container-image ${{ inputs.container-image }}
+          --container-image ${{ inputs.container-image }} \
+          --hf-home /mnt/datadrive/TestData/nemo-fw/TestData/HF_HOME
 
         RUN_TEST_EOF
         )
@@ -186,6 +187,7 @@ runs:
           --platform dgx_h100 \
           --container-image ${{ inputs.container-image }} \
           --data-dir /mnt/datadrive/TestData/megatron-lm/artifacts \
+          --hf-home /mnt/datadrive/TestData/nemo-fw/TestData/HF_HOME
 
         RUN_TEST_EOF
         )

.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", "FDecaYed", "HaochenYuan", "ISEEKYAN", "JRD971000", "Phlip79", "QiZhangNV", "RPrenger", "ShriyaRishab", "Victarry", "Wohox", "ZhiyuLi-Nvidia", "ahmadki", "aklife97", "ananthsub", "asolergi-nv", "buptzyb", "chtruong814", "cspades", "cuichenx", "deepakn94", "dimapihtar", "dingqingy-nv", "duncanriach", "erhoo82", "ericharper", "fanshiqing", "faradawn", "frsun-nvda", "gautham-kollu", "gdengk", "guyueh1", "hxbai", "ilml", "jalbericiola", "janEbert", "jaredcasper", "jenchen13", "jiemingz", "jingqiny-99", "jkamalu", "jon-barker", "jstjohn", "kanz-nv", "kevalmorabia97", "ko3n1g", "kunlunl", "kvareddy", "kwyss-nvidia", "layalir", "lhb8125", "lmcafee-nvidia", "maanug-nv", "mathemakitten", "matthieule", "mchrzanowski", "mehraakash", "mkhona-nvidia", "parthmannan", "prajwal1210", "pthombre", "rogerwaleffe", "sajadn", "sanandaraj5597", "sancha", "santhnm2", "sbak5", "shanmugamr1992", "sharathts", "shengf-nv", "shifangx", "shjwudp", "sidsingh-nvidia", "skyw", "sudhakarsingh27", "tdene", "theothermike", "thomasdhc", "trintamaki", "tylerpoon", "wdykas", "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", "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", "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"]

.github/oncall_schedule.json

@@ -1,16 +1,4 @@
 [
-    {
-        "user": "janEbert",
-        "date": "2026-02-18"
-    },
-    {
-        "user": "asolergi-nv",
-        "date": "2026-02-25"
-    },
-    {
-        "user": "BoxiangW",
-        "date": "2026-03-04"
-    },
     {
         "user": "maanug-nv",
         "date": "2026-03-11"
@@ -20,31 +8,43 @@
         "date": "2026-03-18"
     },
     {
-        "user": "gautham-kollu",
+        "user": "janEbert",
         "date": "2026-03-25"
     },
     {
-        "user": "janEbert",
+        "user": "gautham-kollu",
         "date": "2026-04-01"
     },
     {
-        "user": "maanug-nv",
+        "user": "ilml",
         "date": "2026-04-08"
     },
     {
-        "user": "BoxiangW",
+        "user": "Phlip79",
         "date": "2026-04-15"
     },
     {
-        "user": "Phlip79",
+        "user": "asolergi-nv",
         "date": "2026-04-22"
     },
     {
-        "user": "asolergi-nv",
+        "user": "BoxiangW",
         "date": "2026-04-29"
     },
     {
-        "user": "dimapihtar",
+        "user": "maanug-nv",
         "date": "2026-05-06"
+    },
+    {
+        "user": "dimapihtar",
+        "date": "2026-05-13"
+    },
+    {
+        "user": "gautham-kollu",
+        "date": "2026-05-20"
+    },
+    {
+        "user": "ilml",
+        "date": "2026-05-27"
     }
 ]

.github/pull_request_template.md

@@ -5,19 +5,8 @@
 
 ## Contribution process
 
-```mermaid
-flowchart LR
-    A[Pre-checks] --> B[PR Tests]
-    subgraph Code Review/Approval
-        C1[Expert Review] --> C2[Final Review]
-    end
-    B --> C1
-    C2 --> D[Merge]
-```
-
 ### Pre-checks
 
-- [ ] I want this PR in a versioned release and have added the appropriate Milestone (e.g., `Core 0.8`)
 - [ ] I have added relevant unit tests
 - [ ] I have added relevant functional tests
 - [ ] I have added proper typing to my code [Typing guidelines](https://docs.python.org/3/library/typing.html)
@@ -26,41 +15,36 @@ flowchart LR
 
 ### Code review
 
-The following process is enforced via the CODEOWNERS file for changes into `megatron/core`. For changes outside of `megatron/core`, it is up to the PR author whether or not to tag the Final Reviewer team.
+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!
 
-<details>
-<summary>For MRs into `main` branch</summary>
+All PRs start as **draft**. If you open a non-draft PR, it will be automatically converted to draft.
 
-Feel free to message or comment the @mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!
+#### Step 1: Mark PR as "Ready for Review"
 
-#### (Step 1): Add PR label `Expert Review`
+1. When your PR is ready, click **Ready for Review**.
+2. An oncall reviewer is auto-assigned and expert reviewers are notified based on your changes.
+   - Some PRs may jump straight to step 2. This is determined by `.github/CODEOWNERS`.
 
-#### (Step 2): Collect the expert reviewers reviews
+:warning: Only mark as ready once merge-conflicts are resolved and the CI is passing.
+Final Review might get declined if these requirements are not fulfilled.
 
-1. Attach the `Expert Review` label when your PR is ready for review.
-2. GitHub auto-assigns expert reviewers based on your changes. They will get notified and pick up your PR soon.
+#### Step 2: Final Review
 
-:warning: Only proceed to the next step once all reviewers have approved, merge-conflict are resolved and the CI is passing.  
-Final Review might get declined if these requirements are not fulfilled.
+For PRs that change `megatron/core`, once all expert reviewers have approved, the `Final Review` label is applied **automatically** and final reviewers are assigned.
 
-#### (Step 3): Final Review
+For PRs outside `megatron/core`, this step is skipped.
 
-1. Add `Final Review` label
-2. GitHub auto-assigns final reviewers based on your changes. They will get notified and pick up your PR soon.
+#### Step 3: Approved
 
-#### (Optional Step 4): Cherry-pick into release branch
+Once all required reviewers have approved, the `Approved` label is applied **automatically**.
 
-If this PR also needs to be merged into `core_r*` release branches, after this PR has been merged, select `Cherry-pick` to open a new PR into the release branch.
+### Merge
 
-</details>
+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>
-
-### Merging your PR
-
-Any member of [core-adlr](https://github.com/orgs/teams/NVIDIA/core-adlr) and [`core-nemo`](https://github.com/orgs/teams/NVIDIA/core-nemo) will be able to merge your PR.

.github/workflows/_build_test_publish_wheel.yml

@@ -43,7 +43,7 @@ jobs:
       PUBLISH_DRYRUN: ${{ inputs.dry-run }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref }}
 
@@ -136,7 +136,7 @@ jobs:
           test "${{ steps.build-wheel.outputs.expected-release-number }}" == "$RELEASE_NUMBER"
 
       - name: Upload wheels
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: wheels-${{ matrix.PACKAGE }}-${{ matrix.PLATFORM }}-${{ inputs.dry-run && 'dry-run' || 'release' }}
           path: dist/
@@ -159,7 +159,7 @@ jobs:
       PACKAGE: ${{ matrix.PACKAGE }}
     steps:
       - name: Download wheels
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v7
         with:
           name: wheels-${{ matrix.PACKAGE }}-${{ matrix.PLATFORM }}-${{ inputs.dry-run && 'dry-run' || 'release' }}
           path: dist/

.github/workflows/_release_library.yml

@@ -53,13 +53,34 @@ on:
         description: Starting tag for changelog builder (leave empty for auto-detect)
         type: string
         default: ""
+      publish-docs:
+        required: false
+        description: Publish documentation to S3 after release
+        type: boolean
+        default: true
     secrets:
       TWINE_PASSWORD:
         required: true
       SLACK_WEBHOOK:
         required: true
       PAT:
         required: true
+      AWS_ASSUME_ROLE_ARN:
+        required: true
+      AWS_ACCESS_KEY_ID:
+        required: true
+      AWS_SECRET_ACCESS_KEY:
+        required: true
+      AKAMAI_HOST:
+        required: true
+      AKAMAI_CLIENT_TOKEN:
+        required: true
+      AKAMAI_CLIENT_SECRET:
+        required: true
+      AKAMAI_ACCESS_TOKEN:
+        required: true
+      S3_BUCKET_NAME:
+        required: true
 
 permissions:
   contents: write # To read repository content
@@ -89,7 +110,7 @@ jobs:
       IS_DRY_RUN: ${{ inputs.dry-run }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           path: ${{ github.run_id }}
           token: ${{ secrets.PAT }}
@@ -199,11 +220,8 @@ jobs:
           # Extract PR number from URL
           PR_NUMBER=$(echo $PR_URL | grep -o '[0-9]*$')
 
-          # Add comment to the newly created PR
-          echo gh pr comment $PR_NUMBER --body "/ok to test $(git rev-parse HEAD)"
-
       - name: Wait for status checks on tmp branch
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         id: wait-status
         with:
           github-token: ${{ secrets.PAT }}
@@ -326,7 +344,6 @@ jobs:
       ref: ${{ inputs.release-ref }}
       no-publish: false
     secrets:
-      TWINE_USERNAME: ${{ secrets.TWINE_USERNAME }}
       TWINE_PASSWORD: ${{ secrets.TWINE_PASSWORD }}
 
   create-gh-release:
@@ -344,10 +361,10 @@ jobs:
       REPOSITORY: ${{ github.repository }}
       PROJECT_NAME: Megatron Core
       VERSION: ${{ needs.bump-next-version.outputs.release-version }}
-      TAG_PREFIX: ${{ inputs.gh-release-tag-prefix || '' }}
+      TAG_PREFIX: core_
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           path: ${{ github.run_id }}
           ref: ${{ inputs.release-ref }}
@@ -455,6 +472,12 @@ jobs:
   publish-docs:
     needs: [bump-next-version, create-gh-release]
     uses: ./.github/workflows/release-docs.yml
+    if: |
+      (
+        success() || !failure()
+      )
+      && inputs.publish-docs == true
+      && !cancelled()
     with:
       dry-run: ${{ inputs.dry-run }}
       publish-as-latest: true
@@ -472,7 +495,7 @@ jobs:
       VERSION: ${{ needs.build-test-publish-wheels.outputs.version }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           repository: NVIDIA-NeMo/FW-CI-templates
           ref: v0.17.0

.github/workflows/_update_dependencies.yml

@@ -33,7 +33,7 @@ jobs:
       TARGET_BRANCH: ${{ inputs.target-branch }}
     steps:
       - name: Checkout repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ env.TARGET_BRANCH }}
 
@@ -60,7 +60,7 @@ jobs:
           fi
 
       - name: Checkout repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ env.SOURCE_BRANCH }}
 
@@ -77,7 +77,7 @@ jobs:
           bash -c 'uv lock --upgrade'
 
       - name: Upload lock file
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: lock-file-${{ env.SOURCE_BRANCH }}
           path: uv.lock
@@ -90,7 +90,7 @@ jobs:
       TARGET_BRANCH: ${{ inputs.target-branch }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           token: ${{ secrets.PAT }}
           ref: ${{ env.TARGET_BRANCH }}
@@ -103,7 +103,7 @@ jobs:
           fi
 
       - name: Download lock file
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v7
         with:
           name: lock-file-${{ env.SOURCE_BRANCH }}
 

.github/workflows/auto-reminder-bot.yml

@@ -14,10 +14,10 @@ jobs:
     if: github.repository == 'NVIDIA/Megatron-LM'
     steps:
       - name: Check out repository code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"