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

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

@@ -0,0 +1,36 @@
+# 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. The caller checks the
+  repository out first: a local action is resolved from the workspace, so
+  this action cannot be the job's first step. 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
+        apt-get install -y -qq --no-install-recommends \
+          build-essential ca-certificates curl git pkg-config libclang-dev wget
+
+    - name: Mark the workspace as a safe git directory
+      shell: bash
+      run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
+    - name: Install Rust
+      shell: bash
+      run: |
+        curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
+          | sh -s -- -y --no-modify-path --profile minimal --default-toolchain none
+        echo "${HOME}/.cargo/bin" >> "${GITHUB_PATH}"
+        # Root rust-toolchain.toml is the stable pin. cuda-oxide/ selects the
+        # nightly when a later step sets that working directory.
+        "${HOME}/.cargo/bin/rustup" show
+        (cd cuda-oxide && "${HOME}/.cargo/bin/rustup" show)

.github/workflows/book.yml

@@ -1,21 +1,14 @@
 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]
+    branches:
+      - main
+      - "pull-request/[0-9]+"
     paths:
       - 'cuda-oxide/cuda-oxide-book/**'
       - 'cutile-rs/cutile-book/**'
@@ -39,11 +32,11 @@ 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:
   build:
-    runs-on: ubuntu-latest
+    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 +69,17 @@ 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 +89,7 @@ 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

@@ -4,20 +4,15 @@ 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]
+    branches:
+      - main
+      - "pull-request/[0-9]+"
     paths:
       - 'cuda-oxide/**'
       - 'cuda-bindings/**'

.github/workflows/clippy.yml

@@ -1,39 +1,50 @@
 ---
 name: clippy
 
-# Runs as a job of the top-level CI workflow (.github/workflows/ci.yml),
-# which is the single push/pull_request entry point. Concurrency is governed
-# by CI's own group, so this workflow declares none of its own.
+# Runs as a job of the top-level CI workflow (.github/workflows/ci.yml).
+# Concurrency is governed by CI's own group, so this workflow declares none
+# of its own.
 on:
   workflow_call:
 
 permissions:
   contents: read
 
+# A container job's default shell is dash. The example loop uses bash
+# process substitution.
+defaults:
+  run:
+    shell: bash
+
 jobs:
   clippy:
-    runs-on: ubuntu-latest
+    runs-on: linux-amd64-cpu4
+    # CUDA 13.1.1, the toolkit pin these jobs already used. The devel image
+    # carries nvcc, cudart, and libcurand. rustup is installed in the
+    # container; the image itself has no Rust.
+    container:
+      image: nvidia/cuda:13.1.1-devel-ubuntu24.04
+      env:
+        DEBIAN_FRONTEND: noninteractive
+    env:
+      CUDA_TOOLKIT_PATH: /usr/local/cuda
     timeout-minutes: 30
     steps:
+      # A local action is loaded from the workspace, so checkout comes first.
+      # The CUDA image has no git; without it checkout stores a tarball.
+      - name: Install git
+        run: |
+          apt-get update -qq
+          apt-get install -y -qq --no-install-recommends ca-certificates git
       - name: Clone repository
         uses: actions/checkout@v4
-
-      - name: Install CUDA toolkit
-        uses: Jimver/cuda-toolkit@v0.2.35
-        id: cuda-toolkit
-        with:
-          cuda: "13.1.1"
-          method: network
-          sub-packages: '["nvcc", "cudart-dev"]'
-          non-cuda-sub-packages: '["libcurand-dev"]'
+      - uses: ./.github/actions/setup-cuda-container
 
       # `--all-targets` covers tests, benches and examples, matching the two
       # steps below and the `just clippy` recipe. Without it a lint that fires
       # only in a test target passes here and fails for anyone running the
       # recipe locally.
       - name: Run clippy (workspace crates)
-        env:
-          CUDA_TOOLKIT_PATH: ${{ steps.cuda-toolkit.outputs.CUDA_PATH }}
         working-directory: cuda-oxide
         run: cargo clippy --workspace --all-targets -- -D warnings
 
@@ -55,14 +66,12 @@ jobs:
       # well-defined `target/` under cuda-oxide.
       - name: Run clippy (rustc-codegen-cuda)
         env:
-          CUDA_TOOLKIT_PATH: ${{ steps.cuda-toolkit.outputs.CUDA_PATH }}
           CARGO_TARGET_DIR: ${{ runner.temp }}/clippy-shared-target
         working-directory: cuda-oxide/crates/rustc-codegen-cuda
         run: cargo clippy --all-targets -- -D warnings
 
       - name: Run clippy (rustc-codegen-cuda examples)
         env:
-          CUDA_TOOLKIT_PATH: ${{ steps.cuda-toolkit.outputs.CUDA_PATH }}
           CARGO_TARGET_DIR: ${{ runner.temp }}/clippy-shared-target
         run: |
           set -e