ci: move ubuntu-latest jobs onto linux-amd64-cpu4

.github/actions/setup-cuda-container/action.yml

@@ -0,0 +1,54 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+---
+name: Set up the CUDA devel container
+description: >-
+  Installs the host packages the nvidia/cuda devel image lacks, marks the
+  workspace safe for git, and installs rustup. Callers use the $/ form so
+  this runs before checkout and git is already installed. The image already
+  contains the CUDA toolkit. Later steps pick up rust-toolchain.toml from
+  their working directory.
+
+runs:
+  using: composite
+  steps:
+    - name: Install host packages
+      shell: bash
+      run: |
+        apt-get update -qq
+        # python3 is for sync-example-locks.sh. The image has neither git nor
+        # python3; git has to be present before actions/checkout.
+        apt-get install -y -qq --no-install-recommends \
+          build-essential ca-certificates curl git pkg-config libclang-dev \
+          python3 wget
+
+    - name: Mark the workspace as a safe git directory
+      shell: bash
+      run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
+    - name: Install Rust
+      shell: bash
+      env:
+        RUSTUP_VERSION: "1.29.2"
+        # SHA-256 of rustup-init for x86_64-unknown-linux-gnu, published next to
+        # the binary as .../rustup/archive/1.29.2/x86_64-unknown-linux-gnu/rustup-init.sha256.
+        # Bump both values together.
+        RUSTUP_INIT_SHA256: "5be191e8c70a5007074254cb74d78dbfdd25cd5a61c27de7b8e5410122ec24f4"
+      run: |
+        set -euo pipefail
+        [ "$(uname -m)" = "x86_64" ] || { echo "the rustup-init pin is for x86_64"; exit 1; }
+        init="${RUNNER_TEMP}/rustup-init"
+        curl --proto '=https' --tlsv1.2 -sSfo "${init}" \
+          "https://static.rust-lang.org/rustup/archive/${RUSTUP_VERSION}/x86_64-unknown-linux-gnu/rustup-init"
+        echo "${RUSTUP_INIT_SHA256}  ${init}" | sha256sum -c -
+        chmod +x "${init}"
+        "${init}" -y --no-modify-path --profile minimal --default-toolchain none
+        rm -f "${init}"
+        echo "${HOME}/.cargo/bin" >> "${GITHUB_PATH}"
+        # $/ runs this before the workspace checkout. The action download is
+        # the same commit, and rustup finds rust-toolchain.toml by walking up
+        # from the working directory. The root file is the stable pin;
+        # cuda-oxide/ selects the nightly.
+        repo="${GITHUB_ACTION_PATH}/../../.."
+        (cd "${repo}" && "${HOME}/.cargo/bin/rustup" show)
+        (cd "${repo}/cuda-oxide" && "${HOME}/.cargo/bin/rustup" show)

.github/workflows/book.yml

@@ -1,27 +1,15 @@
 name: Deploy CUDA Rust Docs
 
 # Path-filtered lane: only documentation sources can change what this builds.
+# Self-hosted runners reject pull_request. copy-pr-bot mirrors trusted PRs to
+# pull-request/<n>, and the build job triggers on that push. `deploy` stays on
+# main: a mirror push is a push event, so an event-name check would publish it.
 on:
   push:
-    branches: [main]
-    paths:
-      - 'cuda-oxide/cuda-oxide-book/**'
-      - 'cutile-rs/cutile-book/**'
-      - 'cutile-rs/scripts/build_versioned_book.sh'
-      - 'docs/**'
-      - '.github/workflows/book.yml'
-  # Validate the book on PRs too. The build job alone runs there; `deploy` is
-  # gated below, so a pull request never publishes. Without this the book was
-  # only ever built after merge, so a PR that broke it could not be caught by
-  # review or by CI.
-  pull_request:
-    branches: [main]
-    paths:
-      - 'cuda-oxide/cuda-oxide-book/**'
-      - 'cutile-rs/cutile-book/**'
-      - 'cutile-rs/scripts/build_versioned_book.sh'
-      - 'docs/**'
-      - '.github/workflows/book.yml'
+    # No workflow-level paths: filter; the changes job below gates the jobs.
+    branches:
+      - main
+      - "pull-request/[0-9]+"
   workflow_dispatch:
 
 # Only checkout rights by default. The Pages deployment permissions live on
@@ -39,11 +27,47 @@ permissions:
 # a slower older commit deploy after a newer one and replace the published site.
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
 
 jobs:
+  # Path gate. copy-pr-bot creates pull-request/<n> at an existing SHA, and
+  # GitHub often treats that push as having no path changes, so a workflow-level
+  # `paths:` filter would skip the whole run. This job diffs against main
+  # instead, as cutile-rs.yml does, and every job below runs when no file diff
+  # is detected. Other events (schedule, workflow_dispatch) skip the gate.
+  changes:
+    if: github.event_name == 'push'
+    runs-on: linux-amd64-cpu4
+    timeout-minutes: 5
+    permissions:
+      contents: read
+    outputs:
+      relevant: ${{ steps.changes.outputs.relevant }}
+      any_changed: ${{ steps.changes.outputs.any_changed }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: dorny/paths-filter@0e4a8c6effa4802afeda77dc8d303f8176d7dfad  # v3.0.4
+        id: changes
+        with:
+          filters: |
+            relevant:
+              - 'cuda-oxide/cuda-oxide-book/**'
+              - 'cutile-rs/cutile-book/**'
+              - 'cutile-rs/scripts/build_versioned_book.sh'
+              - 'docs/**'
+              - '.github/workflows/book.yml'
+            # `*` covers a root file, `**` every nested path. Both false means
+            # no file diff was detected.
+            any_changed:
+              - '*'
+              - '**'
+
   build:
-    runs-on: ubuntu-latest
+    needs: changes
+    if: ${{ !cancelled() && (github.event_name != 'push' || needs.changes.outputs.relevant == 'true' || needs.changes.outputs.any_changed != 'true') }}
+    runs-on: linux-amd64-cpu4
     # An umbrella page plus two Sphinx books. Bound the job so a
     # wedged install or a sphinx that never returns fails instead of burning to
     # the 6-hour default.
@@ -76,17 +100,17 @@ jobs:
         run: |
           # Unset CUTILE_DOCS_TAGS → build every tag matching the pattern.
           # Empty CUTILE_DOCS_TAGS → current tree only (fast PR check).
-          if [ "${{ github.event_name }}" = "pull_request" ]; then
-            export CUTILE_DOCS_TAGS=""
-          fi
+          case "${GITHUB_REF}" in
+            refs/heads/pull-request/*) export CUTILE_DOCS_TAGS="" ;;
+          esac
           bash docs/build_all_docs.sh
 
       # Only `deploy` consumes this, and `deploy` is skipped on pull requests,
       # so uploading it there produces an artifact nothing can ever read. A PR's
       # job is to prove both Sphinx builds succeed, which the steps above already
       # did; gate the upload on the same condition `deploy` uses so the two
       # cannot drift apart.
-      - if: github.event_name != 'pull_request'
+      - if: github.ref == 'refs/heads/main'
         uses: actions/upload-pages-artifact@v3
         with:
           path: docs/build/html
@@ -96,7 +120,7 @@ jobs:
     # Publishing is for main only. A pull request builds the book to prove it
     # is sound and stops there; it never touches the Pages environment or
     # holds the deployment permissions below.
-    if: github.event_name != 'pull_request'
+    if: github.ref == 'refs/heads/main'
     permissions:
       pages: write
       id-token: write

.github/workflows/cargo-deny.yml

@@ -1,8 +1,8 @@
 ---
 name: cargo-deny
 
-# Runs as a job of the top-level CI workflow (.github/workflows/ci.yml) on
-# push/pull_request, plus a standalone weekly security scan via schedule.
+# Runs as a job of the top-level CI workflow (.github/workflows/ci.yml),
+# plus a standalone weekly security scan via schedule.
 # Concurrency for the CI path is governed by CI's own group.
 #
 # Four parts of the same concern. `check` enforces the license *policy* over
@@ -30,14 +30,24 @@ on:
 permissions:
   contents: read
 
+# A container job's default shell is dash; use bash, as on ubuntu-latest.
+defaults:
+  run:
+    shell: bash
+
 jobs:
   check:
-    runs-on: ubuntu-latest
+    runs-on: linux-amd64-cpu4
+    container:
+      image: rust:1.98.0-bookworm
     timeout-minutes: 10
     steps:
       - name: Clone repository
         uses: actions/checkout@v4
 
+      - name: Mark the workspace as a safe git directory
+        run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
       - name: Install cargo-deny
         run: cargo install cargo-deny --locked
 
@@ -94,25 +104,35 @@ jobs:
 
   license-manifest:
     name: dependency-licenses.csv covers every declared crate
-    runs-on: ubuntu-latest
+    runs-on: linux-amd64-cpu4
+    container:
+      image: rust:1.98.0-bookworm
     timeout-minutes: 10
     steps:
       - name: Clone repository
         uses: actions/checkout@v4
 
+      - name: Mark the workspace as a safe git directory
+        run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
       # Only reads manifests: `cargo metadata` resolves the graph without
       # running build scripts, so this needs no CUDA toolkit and no LLVM.
       - name: Verify the license inventory covers the workspace
         run: bash cuda-oxide/scripts/check-dependency-licenses.sh
 
   example-policy:
     name: deny.toml governs the example workspaces
-    runs-on: ubuntu-latest
+    runs-on: linux-amd64-cpu4
+    container:
+      image: rust:1.98.0-bookworm
     timeout-minutes: 15
     steps:
       - name: Clone repository
         uses: actions/checkout@v4
 
+      - name: Mark the workspace as a safe git directory
+        run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
       - name: Install cargo-deny
         run: cargo install cargo-deny --locked
 
@@ -125,12 +145,17 @@ jobs:
 
   source-headers:
     name: every source file carries the SPDX header
-    runs-on: ubuntu-latest
+    runs-on: linux-amd64-cpu4
+    container:
+      image: rust:1.98.0-bookworm
     timeout-minutes: 5
     steps:
       - name: Clone repository
         uses: actions/checkout@v4
 
+      - name: Mark the workspace as a safe git directory
+        run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
       # Pure text check over tracked files: no toolchain, no network. The OSRB
       # review fixed 32 missing headers in #812 and the next two scripts to
       # land (#819, #835) drifted again; this makes the third time the last.

.github/workflows/ci-status.yml

@@ -5,11 +5,9 @@ name: CI status
 
 # One status for the whole repository, so the README needs one badge.
 #
-# Badges are per workflow file, and the two pipelines have to stay separate
-# for now: ci.yml (SIMT and the shared host crates) runs on GitHub-hosted
-# runners on push and pull_request; cutile-rs.yml (Tile) runs on NVIDIA
-# self-hosted runners, which cannot run on pull_request events, so it
-# triggers on push to main and to the copy-pr-bot mirror branches.
+# Badges are per workflow file. ci.yml and cutile-rs.yml both run on NVIDIA
+# self-hosted runners, which reject pull_request, so both trigger on push to
+# main and to the copy-pr-bot mirror branches.
 #
 # This workflow runs whenever either of them completes on main. For each
 # pipeline it finds the newest completed push run on main that actually
@@ -34,7 +32,7 @@ permissions:
 jobs:
   status:
     name: combined CI status on main
-    runs-on: ubuntu-latest
+    runs-on: linux-amd64-cpu4
     timeout-minutes: 5
     steps:
       - name: Report the newest executed main run of each pipeline

.github/workflows/ci.yml

@@ -4,29 +4,16 @@ name: CI
 # Path-filtered SIMT lane: skip when a change cannot affect cuda-oxide or the
 # shared host crates. `cuda-oxide/**` is deliberately broad (prose as well as
 # code) because guard scripts cross-check the book against the crates.
+#
+# Self-hosted runners reject pull_request. copy-pr-bot mirrors trusted PRs to
+# pull-request/<n>, and this workflow triggers on that push
+# (config: .github/copy-pr-bot.yaml).
 on:
   push:
-    branches: [main]
-    paths:
-      - 'cuda-oxide/**'
-      - 'cuda-bindings/**'
-      - 'cuda-core/**'
-      - 'cuda-core-derive/**'
-      - 'cuda-async/**'
-      - 'Cargo.toml'
-      - 'Cargo.lock'
-      - '.github/workflows/**'
-  pull_request:
-    branches: [main]
-    paths:
-      - 'cuda-oxide/**'
-      - 'cuda-bindings/**'
-      - 'cuda-core/**'
-      - 'cuda-core-derive/**'
-      - 'cuda-async/**'
-      - 'Cargo.toml'
-      - 'Cargo.lock'
-      - '.github/workflows/**'
+    # No workflow-level paths: filter; the changes job below gates the jobs.
+    branches:
+      - main
+      - "pull-request/[0-9]+"
 
 # Each commit on main gets its own group, so it starts at once. Any other ref
 # still shares one group and cancels the older run.
@@ -44,14 +31,60 @@ permissions:
   contents: read
 
 jobs:
+  # Path gate. copy-pr-bot creates pull-request/<n> at an existing SHA, and
+  # GitHub often treats that push as having no path changes, so a workflow-level
+  # `paths:` filter would skip the whole run. This job diffs against main
+  # instead, as cutile-rs.yml does, and every job below runs when no file diff
+  # is detected. Other events (schedule, workflow_dispatch) skip the gate.
+  changes:
+    if: github.event_name == 'push'
+    runs-on: linux-amd64-cpu4
+    timeout-minutes: 5
+    permissions:
+      contents: read
+    outputs:
+      relevant: ${{ steps.changes.outputs.relevant }}
+      any_changed: ${{ steps.changes.outputs.any_changed }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: dorny/paths-filter@0e4a8c6effa4802afeda77dc8d303f8176d7dfad  # v3.0.4
+        id: changes
+        with:
+          filters: |
+            relevant:
+              - 'cuda-oxide/**'
+              - 'cuda-bindings/**'
+              - 'cuda-core/**'
+              - 'cuda-core-derive/**'
+              - 'cuda-async/**'
+              - 'Cargo.toml'
+              - 'Cargo.lock'
+              - '.github/workflows/**'
+              - '.github/actions/setup-cuda-container/**'
+            # `*` covers a root file, `**` every nested path. Both false means
+            # no file diff was detected.
+            any_changed:
+              - '*'
+              - '**'
+
   fmt:
+    needs: changes
+    if: ${{ !cancelled() && (github.event_name != 'push' || needs.changes.outputs.relevant == 'true' || needs.changes.outputs.any_changed != 'true') }}
     uses: ./.github/workflows/fmt.yml
 
   clippy:
+    needs: changes
+    if: ${{ !cancelled() && (github.event_name != 'push' || needs.changes.outputs.relevant == 'true' || needs.changes.outputs.any_changed != 'true') }}
     uses: ./.github/workflows/clippy.yml
 
   unit-tests:
+    needs: changes
+    if: ${{ !cancelled() && (github.event_name != 'push' || needs.changes.outputs.relevant == 'true' || needs.changes.outputs.any_changed != 'true') }}
     uses: ./.github/workflows/unit-tests.yml
 
   cargo-deny:
+    needs: changes
+    if: ${{ !cancelled() && (github.event_name != 'push' || needs.changes.outputs.relevant == 'true' || needs.changes.outputs.any_changed != 'true') }}
     uses: ./.github/workflows/cargo-deny.yml