Merge remote-tracking branch 'origin/main' into refactor-mempool-hierarchy

Author: Andy-Jost

.github/actions/fetch_ctk/action.yml

@@ -14,7 +14,7 @@ inputs:
   cuda-components:
     description: "A list of the CTK components to install as a comma-separated list. e.g. 'cuda_nvcc,cuda_nvrtc,cuda_cudart'"
     required: false
-    default: "cuda_nvcc,cuda_cudart,cuda_crt,libnvvm,cuda_nvrtc,cuda_profiler_api,cuda_cccl,libnvjitlink,libcufile,libnvfatbin"
+    default: "cuda_nvcc,cuda_cudart,cuda_crt,libnvvm,cuda_nvrtc,cuda_profiler_api,cuda_cccl,cuda_cupti,libnvjitlink,libcufile,libnvfatbin"
   cuda-path:
     description: "where the CTK components will be installed to, relative to $PWD"
     required: false

.github/workflows/bandit.yml

@@ -42,6 +42,6 @@ jobs:
         with:
           args: "check --select S --ignore ${{ steps.ignore-codes.outputs.codes }} --output-format sarif --output-file results.sarif"
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@v4.32.4
+        uses: github/codeql-action/upload-sarif@v4.32.5
         with:
           sarif_file: results.sarif

.github/workflows/build-wheel.yml

@@ -369,7 +369,7 @@ jobs:
 
           OLD_BRANCH=$(yq '.backport_branch' ci/versions.yml)
           OLD_BASENAME="cuda-bindings-python${PYTHON_VERSION_FORMATTED}-cuda*-${{ inputs.host-platform }}*"
-          LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "ci.yml" -s completed -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')
+          LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "ci.yml" -s success -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')
           if [[ "$LATEST_PRIOR_RUN_ID" == "" ]]; then
             echo "LATEST_PRIOR_RUN_ID not found!"
             exit 1

.github/workflows/codeql.yml

@@ -31,13 +31,13 @@ jobs:
       uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@0ec47d036c68ae0cf94c629009b1029407111281  # v3.31.8
+      uses: github/codeql-action/init@40f0fa95c41fede7b43f035cb47aac899ee0ba0a  # v3.31.8
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
         queries: security-extended
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@0ec47d036c68ae0cf94c629009b1029407111281  # v3.31.8
+      uses: github/codeql-action/analyze@40f0fa95c41fede7b43f035cb47aac899ee0ba0a  # v3.31.8
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/coverage.yml

@@ -98,7 +98,8 @@ jobs:
 
       - name: Build cuda-pathfinder
         run: |
-          .venv/bin/pip install -v ./cuda_pathfinder --group test
+          cd cuda_pathfinder
+          ../.venv/bin/pip install -v . --group test
 
       - name: Build cuda-bindings
         run: |

.github/workflows/test-wheel-linux.yml

@@ -151,7 +151,7 @@ jobs:
 
           OLD_BRANCH=${{ needs.compute-matrix.outputs.OLD_BRANCH }}
           OLD_BASENAME="cuda-bindings-python${PYTHON_VERSION_FORMATTED}-cuda*-${{ inputs.host-platform }}*"
-          LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "ci.yml" -s completed -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')
+          LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "ci.yml" -s success -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')
           if [[ "$LATEST_PRIOR_RUN_ID" == "" ]]; then
             echo "LATEST_PRIOR_RUN_ID not found!"
             exit 1

.github/workflows/test-wheel-windows.yml

@@ -137,7 +137,7 @@ jobs:
         run: |
           $OLD_BRANCH = yq '.backport_branch' ci/versions.yml
           $OLD_BASENAME = "cuda-bindings-python${env:PYTHON_VERSION_FORMATTED}-cuda*-${{ inputs.host-platform }}*"
-          $runData = gh run list -b $OLD_BRANCH -L 1 -w "ci.yml" -s completed -R NVIDIA/cuda-python --json databaseId | ConvertFrom-Json
+          $runData = gh run list -b $OLD_BRANCH -L 1 -w "ci.yml" -s success -R NVIDIA/cuda-python --json databaseId | ConvertFrom-Json
           if (-not $runData -or $runData.Length -eq 0 -or -not $runData[0].databaseId -or [string]::IsNullOrEmpty($runData[0].databaseId)) {
               Write-Host "LATEST_PRIOR_RUN_ID not found!"
               exit 1

AGENTS.md

@@ -0,0 +1 @@
+AGENTS.md

CLAUDE.md

@@ -0,0 +1,67 @@
+This file describes `cuda_bindings`, the low-level CUDA host API bindings
+subpackage in the `cuda-python` monorepo.
+
+## Scope and principles
+
+- **Role**: provide low-level, close-to-CUDA interfaces under
+  `cuda.bindings.*` with broad API coverage.
+- **Style**: prioritize correctness and API compatibility over convenience
+  wrappers. High-level ergonomics belong in `cuda_core`, not here.
+- **Cross-platform**: preserve Linux and Windows behavior unless a change is
+  intentionally platform-specific.
+
+## Package architecture
+
+- **Public module layer**: Cython modules under `cuda/bindings/` expose user
+  APIs (`driver`, `runtime`, `nvrtc`, `nvjitlink`, `nvvm`, `cufile`, etc.).
+- **Internal binding layer**: `cuda/bindings/_bindings/` provides lower-level
+  glue and loader helpers used by public modules.
+- **Platform internals**: `cuda/bindings/_internal/` contains
+  platform-specific implementation files and support code.
+- **Build/codegen backend**: `build_hooks.py` drives header parsing, template
+  expansion, extension configuration, and Cythonization.
+
+## Generated-source workflow
+
+- **Do not hand-edit generated binding files**: many files under
+  `cuda/bindings/` (including `*.pyx`, `*.pxd`, `*.pyx.in`, and `*.pxd.in`)
+  are generated artifacts.
+- **Generated files are synchronized from another repository**: changes to these
+  files in this repo are expected to be overwritten by the next sync.
+- **If generated output must change**: make the change at the generation source
+  and sync the updated artifacts back here, rather than patching generated files
+  directly in this repo.
+- **Header-driven generation**: parser behavior and required CUDA headers are
+  defined in `build_hooks.py`; update those rules when introducing new symbols.
+- **Platform split files**: keep `_linux.pyx` and `_windows.pyx` variants
+  aligned when behavior should be equivalent.
+
+## Testing expectations
+
+- **Primary tests**: `pytest tests/`
+- **Cython tests**:
+  - build: `tests/cython/build_tests.sh` (or platform equivalent)
+  - run: `pytest tests/cython/`
+- **Examples**: example coverage is pytest-based under `examples/`.
+- **Benchmarks**: run with `pytest --benchmark-only benchmarks/` when needed.
+- **Orchestrated run**: from repo root, `scripts/run_tests.sh bindings`.
+
+## Build and environment notes
+
+- `CUDA_HOME` or `CUDA_PATH` must point to a valid CUDA Toolkit for source
+  builds that parse headers.
+- `CUDA_PYTHON_PARALLEL_LEVEL` controls build parallelism.
+- `CUDA_PYTHON_PARSER_CACHING` controls parser-cache behavior during generation.
+- Runtime behavior is affected by
+  `CUDA_PYTHON_CUDA_PER_THREAD_DEFAULT_STREAM` and
+  `CUDA_PYTHON_DISABLE_MAJOR_VERSION_WARNING`.
+
+## Editing guidance
+
+- Keep CUDA return/error semantics explicit and avoid broad fallback behavior.
+- Reuse existing helper layers (`_bindings`, `_internal`, `_lib`) before adding
+  new one-off utilities.
+- If you add or change exported APIs, update relevant docs under
+  `docs/source/module/` and tests in `tests/`.
+- Prefer changes that are easy to regenerate/rebuild rather than patching
+  generated output directly.