Merge branch 'main' into update-linker-options-sequence-handling

Author: leofang

.github/ISSUE_TEMPLATE/release_checklist.yml

@@ -1,39 +1,33 @@
 name: Release Checklist
-description: Release managers need to go through this check list and ensure all tasks are done
+description: Public checklist for release managers making a subpackage release
+labels: ["P0"]
+
 body:
   - type: markdown
     attributes:
       value: |
-        Please go through this checklist and ensure all tasks are completed.
-
-  - type: checkboxes
-    id: cuda-bindings-tasks
-    attributes:
-      label: Tasks for cuda-bindings / cuda-python release
-      options:
-        - label: "Push any internal updates for accommodating a new CTK release to the public (**IMPORTANT**: Need to wait for CTK posting!)"
-        - label: "If it is a major release, create a new branch to backport to and update the branch name [here](../BACKPORT_BRANCH)"
-        - label: Follow the check list for `cuda-core` below for the remaining steps
+        This checklist is for cuda-core releases as well as cuda-bindings patches. Please go through this checklist and ensure all tasks are completed.
 
   - type: checkboxes
-    id: cuda-core-tasks
+    id: subpackage-tasks
     attributes:
-      label: Tasks for cuda-core release
+      label: Tasks for cuda-core and cuda-bindings patch release
       options:
         - label: File an internal nvbug to communicate test plan & release schedule with QA
         - label: Ensure all pending PRs are reviewed, tested, and merged
-        - label: Update the dependency requirements, if needed
+        - label: Check (or update if needed) the dependency requirements
         - label: Bump the version
         - label: Create a public rc tag
         - label: "Point QA to fetch public artifacts (wheels) from the GHA run ID, example: `gh run download 12323257563 -p \"cuda-core*\" -R NVIDIA/cuda-python`"
         - label: Wait for QA reports and fix any issues found
-        - label: Finalize the doc update, including release notes
+        - label: "Finalize the doc update, including release notes (\"Note: Touching docstrings/type annotations in code is OK during code freeze, apply your best judgement!\")"
         - label: Update the docs for the new version
         - label: Create a public release tag
         - label: If any code change happens, rebuild the wheels from the new tag
+        - label: Update the conda recipe & release conda packages
+        - label: Upload conda packages to nvidia channel
         - label: Upload wheels to PyPI
+        - label: Post-release QA
         - label: Finalize the announcement update
         - label: Send out the announcement internally
         - label: Send out the announcement externally (GitHub Release -> Announcement)
-        - label: Update the conda recipe & release conda packages
-        - label: Post-release QA

.github/actions/fetch_ctk/action.yml

@@ -123,4 +123,4 @@ runs:
         echo "CUDA_PATH=${CUDA_PATH}" >> $GITHUB_ENV
         echo "CUDA_HOME=${CUDA_PATH}" >> $GITHUB_ENV
         echo "${CUDA_PATH}/bin" >> $GITHUB_PATH
-        echo "LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}:${CUDA_PATH}/lib" >> $GITHUB_ENV
+        echo "LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}:${CUDA_PATH}/lib:${CUDA_PATH}/nvvm/lib64" >> $GITHUB_ENV

.github/workflows/build-docs.yml

@@ -37,17 +37,11 @@ jobs:
     name: Build docs
     # The build stage could fail but we want the CI to keep moving.
     if: ${{ github.repository_owner == 'nvidia' && !cancelled() }}
-    # WAR: Building the doc currently requires a GPU (NVIDIA/cuda-python#326,327)
-    runs-on: linux-amd64-gpu-t4-latest-1
-    #runs-on: ubuntu-latest
+    runs-on: ubuntu-latest
     defaults:
       run:
         shell: bash -el {0}
     steps:
-      # WAR: Building the doc currently requires a GPU (NVIDIA/cuda-python#326,327)
-      - name: Ensure GPU is working
-        run: nvidia-smi
-
       - name: Checkout ${{ github.event.repository.name }}
         uses: actions/checkout@v4
         with:

cuda_bindings/cuda/bindings/_internal/nvvm.pxd

@@ -0,0 +1,25 @@
+# Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
+#
+# SPDX-License-Identifier: LicenseRef-NVIDIA-SOFTWARE-LICENSE
+#
+# This code was automatically generated across versions from 11.0.3 to 12.8.0. Do not modify it directly.
+
+from ..cynvvm cimport *
+
+
+###############################################################################
+# Wrapper functions
+###############################################################################
+
+cdef nvvmResult _nvvmVersion(int* major, int* minor) except* nogil
+cdef nvvmResult _nvvmIRVersion(int* majorIR, int* minorIR, int* majorDbg, int* minorDbg) except* nogil
+cdef nvvmResult _nvvmCreateProgram(nvvmProgram* prog) except* nogil
+cdef nvvmResult _nvvmDestroyProgram(nvvmProgram* prog) except* nogil
+cdef nvvmResult _nvvmAddModuleToProgram(nvvmProgram prog, const char* buffer, size_t size, const char* name) except* nogil
+cdef nvvmResult _nvvmLazyAddModuleToProgram(nvvmProgram prog, const char* buffer, size_t size, const char* name) except* nogil
+cdef nvvmResult _nvvmCompileProgram(nvvmProgram prog, int numOptions, const char** options) except* nogil
+cdef nvvmResult _nvvmVerifyProgram(nvvmProgram prog, int numOptions, const char** options) except* nogil
+cdef nvvmResult _nvvmGetCompiledResultSize(nvvmProgram prog, size_t* bufferSizeRet) except* nogil
+cdef nvvmResult _nvvmGetCompiledResult(nvvmProgram prog, char* buffer) except* nogil
+cdef nvvmResult _nvvmGetProgramLogSize(nvvmProgram prog, size_t* bufferSizeRet) except* nogil
+cdef nvvmResult _nvvmGetProgramLog(nvvmProgram prog, char* buffer) except* nogil