Merge branch 'main' into pathfinder_compatibility_guard_rails

Author: rwgk

.github/workflows/ci.yml

@@ -343,7 +343,7 @@ jobs:
       build-type: pull-request
       host-platform: ${{ matrix.host-platform }}
       build-ctk-ver: ${{ needs.ci-vars.outputs.CUDA_BUILD_VER }}
-      nruns: ${{ (github.event_name == 'schedule' && 100) || 1}}
+      nruns: ${{ (github.event_name == 'schedule' && 5) || 1}}
       skip-bindings-test: ${{ !fromJSON(needs.detect-changes.outputs.test_bindings) }}
 
   # See test-linux-64 for why test jobs are split by platform.
@@ -368,7 +368,7 @@ jobs:
       build-type: pull-request
       host-platform: ${{ matrix.host-platform }}
       build-ctk-ver: ${{ needs.ci-vars.outputs.CUDA_BUILD_VER }}
-      nruns: ${{ (github.event_name == 'schedule' && 100) || 1}}
+      nruns: ${{ (github.event_name == 'schedule' && 5) || 1}}
       skip-bindings-test: ${{ !fromJSON(needs.detect-changes.outputs.test_bindings) }}
 
   # See test-linux-64 for why test jobs are split by platform.
@@ -393,7 +393,7 @@ jobs:
       build-type: pull-request
       host-platform: ${{ matrix.host-platform }}
       build-ctk-ver: ${{ needs.ci-vars.outputs.CUDA_BUILD_VER }}
-      nruns: ${{ (github.event_name == 'schedule' && 100) || 1}}
+      nruns: ${{ (github.event_name == 'schedule' && 5) || 1}}
       skip-bindings-test: ${{ !fromJSON(needs.detect-changes.outputs.test_bindings) }}
 
   doc:

.github/workflows/release.yml

@@ -20,7 +20,6 @@ on:
           - cuda-bindings
           - cuda-pathfinder
           - cuda-python
-          - all
       git-tag:
         description: "The release git tag"
         required: true
@@ -89,6 +88,30 @@ jobs:
             gh release create "${{ inputs.git-tag }}" --draft --repo "${{ github.repository }}" --title "Release ${{ inputs.git-tag }}" --notes "Release ${{ inputs.git-tag }}"
           fi
 
+  check-release-notes:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Source
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          ref: ${{ inputs.git-tag }}
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Self-test release-notes checker
+        run: |
+          pip install pytest
+          pytest ci/tools/tests
+
+      - name: Check versioned release notes exist
+        run: |
+          python ci/tools/check_release_notes.py \
+            --git-tag "${{ inputs.git-tag }}" \
+            --component "${{ inputs.component }}"
+
   doc:
     name: Build release docs
     if: ${{ github.repository_owner == 'nvidia' }}
@@ -99,6 +122,7 @@ jobs:
       pull-requests: write
     needs:
       - check-tag
+      - check-release-notes
       - determine-run-id
     secrets: inherit
     uses: ./.github/workflows/build-docs.yml
@@ -114,6 +138,7 @@ jobs:
       contents: write
     needs:
       - check-tag
+      - check-release-notes
       - determine-run-id
       - doc
     secrets: inherit
@@ -128,11 +153,12 @@ jobs:
     runs-on: ubuntu-latest
     needs:
       - check-tag
+      - check-release-notes
       - determine-run-id
       - doc
     environment:
       name: testpypi
-      url: https://test.pypi.org/${{ inputs.component != 'all' && format('p/{0}/', inputs.component) || '' }}
+      url: https://test.pypi.org/p/${{ inputs.component }}/
     permissions:
       id-token: write
     steps:
@@ -162,7 +188,7 @@ jobs:
       - publish-testpypi
     environment:
       name: pypi
-      url: https://pypi.org/${{ inputs.component != 'all' && format('p/{0}/', inputs.component) || '' }}
+      url: https://pypi.org/p/${{ inputs.component }}/
     permissions:
       id-token: write
     steps:

benchmarks/cuda_bindings/README.md

@@ -6,9 +6,13 @@ Driver APIs through cuda.bindings, relative to a similar C++ baseline.
 The goal is to benchmark how much overhead does the Python layer adds to calling
 CUDA APIs and what operations are not in our target of less than 1us of overhead.
 
-Each Python benchmark has a C++ counterpart, which is used to compare the
-operations. We try to make each implementation perform small operations
-and nearly the same work as possible and are run under similar conditions.
+Most Python benchmarks have a C++ counterpart that is used as a comparative
+baseline. We try to make each implementation perform small operations and
+nearly the same work as possible and are run under similar conditions.
+
+A few benchmarks (e.g. in `bench_enum.py`) are intentionally Python-only
+because they measure costs with no direct C++ equivalent — such as enum
+construction and member access on `cuda.bindings` enum classes.
 
 These are **not** throughput benchmarks to measure the overall performance
 of kernels and applications.

benchmarks/cuda_bindings/benchmarks/bench_ctx_device.py

@@ -13,6 +13,11 @@
 _, DEVICE = cuda.cuDeviceGet(0)
 ATTRIBUTE = cuda.CUdevice_attribute.CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR
 
+# Outer retain so the benchmarked retain/release pair just bumps the refcount.
+_err, _PRIMARY_CTX = cuda.cuDevicePrimaryCtxRetain(DEVICE)
+if _err != cuda.CUresult.CUDA_SUCCESS:
+    raise RuntimeError(f"cuDevicePrimaryCtxRetain failed during setup: {_err}")
+
 
 def bench_ctx_get_current(loops: int) -> float:
     _fn = cuda.cuCtxGetCurrent
@@ -60,3 +65,15 @@ def bench_device_get_attribute(loops: int) -> float:
     for _ in range(loops):
         _fn(_attr, _dev)
     return time.perf_counter() - t0
+
+
+def bench_device_primary_ctx_retain(loops: int) -> float:
+    _retain = cuda.cuDevicePrimaryCtxRetain
+    _release = cuda.cuDevicePrimaryCtxRelease
+    _dev = DEVICE
+
+    t0 = time.perf_counter()
+    for _ in range(loops):
+        _retain(_dev)
+        _release(_dev)
+    return time.perf_counter() - t0

benchmarks/cuda_bindings/benchmarks/bench_enum.py

@@ -0,0 +1,34 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import time
+
+from cuda.bindings import driver as cuda
+
+
+def bench_curesult_construction(loops: int) -> float:
+    _cls = cuda.CUresult
+
+    t0 = time.perf_counter()
+    for _ in range(loops):
+        _cls(0)
+    return time.perf_counter() - t0
+
+
+def bench_curesult_member_access(loops: int) -> float:
+    _cls = cuda.CUresult
+
+    t0 = time.perf_counter()
+    for _ in range(loops):
+        _cls.CUDA_SUCCESS  # noqa: B018
+    return time.perf_counter() - t0
+
+
+def bench_device_attribute_construction(loops: int) -> float:
+    _cls = cuda.CUdevice_attribute
+
+    t0 = time.perf_counter()
+    for _ in range(loops):
+        _cls(1)
+    return time.perf_counter() - t0

benchmarks/cuda_bindings/benchmarks/bench_pointer_attributes.py

@@ -12,6 +12,14 @@
 PTR = alloc_persistent(1 << 18)
 ATTRIBUTE = cuda.CUpointer_attribute.CU_POINTER_ATTRIBUTE_MEMORY_TYPE
 
+ATTRIBUTES = (
+    cuda.CUpointer_attribute.CU_POINTER_ATTRIBUTE_MEMORY_TYPE,
+    cuda.CUpointer_attribute.CU_POINTER_ATTRIBUTE_DEVICE_POINTER,
+    cuda.CUpointer_attribute.CU_POINTER_ATTRIBUTE_HOST_POINTER,
+    cuda.CUpointer_attribute.CU_POINTER_ATTRIBUTE_BUFFER_ID,
+)
+NUM_ATTRIBUTES = len(ATTRIBUTES)
+
 
 def bench_pointer_get_attribute(loops: int) -> float:
     # Local references to avoid global lookups in the hot loop
@@ -23,3 +31,15 @@ def bench_pointer_get_attribute(loops: int) -> float:
     for _ in range(loops):
         _fn(_attr, _ptr)
     return time.perf_counter() - t0
+
+
+def bench_pointer_get_attributes(loops: int) -> float:
+    _fn = cuda.cuPointerGetAttributes
+    _num = NUM_ATTRIBUTES
+    _attrs = ATTRIBUTES
+    _ptr = PTR
+
+    t0 = time.perf_counter()
+    for _ in range(loops):
+        _fn(_num, _attrs, _ptr)
+    return time.perf_counter() - t0