Merge branch 'main' into update_trt_decoder_yaml

Signed-off-by: Scott Thornton <wsttiger@gmail.com>

Author: wsttiger

.cudaq_realtime_version

@@ -1,6 +1,6 @@
 {
   "cudaq_realtime": {
     "repository": "NVIDIA/cuda-quantum",
-    "ref": "cd88025b3d1beb02ca2703de70a583e647af10fb"
+    "ref": "053480dda0413c219c224d42313aa14d7a17a7fe"
   }
 }

.cudaq_version

@@ -1,6 +1,6 @@
 {
   "cudaq": {
     "repository": "NVIDIA/cuda-quantum",
-    "ref": "cd88025b3d1beb02ca2703de70a583e647af10fb"
+    "ref": "67404cea365c0f78a9319f89ef634afca15011c8"
   }
 }

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,61 @@
+<!--
+Thanks for contributing to CUDA-Q Libraries!
+
+Please read the full Pull Request Guidelines in Contributing.md:
+https://github.com/NVIDIA/cudaqx/blob/main/Contributing.md#pull-request-guidelines
+-->
+
+## Description
+
+<!-- What does this PR change, and why? Link related issues. -->
+
+## Runtime / performance impact
+
+<!--
+If this change affects performance, paste benchmark numbers here.
+Otherwise write "N/A".
+-->
+
+## Self-review checklist
+
+Please confirm each item before requesting review. Check `[x]` or strike
+through and explain.
+
+### Before requesting review
+- [ ] I reviewed my own full diff in GitHub or my editor.
+- [ ] PR is in Draft if it is not yet ready for review.
+- [ ] Temporary / debugging changes have been removed.
+- [ ] Local test logs reviewed; no unexplained warnings or errors.
+- [ ] CI logs reviewed; no unexplained warnings or errors.
+- [ ] Full CI has been run.
+
+### Scope and size
+- [ ] PR is under ~1000 lines, or an exception is justified in the description.
+- [ ] Refactoring-only changes are isolated in their own PR(s).
+- [ ] No existing tests were disabled or modified just to make this PR pass
+      (if so, an issue has been raised).
+
+### Tests
+- [ ] New functionality has new tests.
+- [ ] Tests fail if the new functionality is broken (including crashes), not
+      just when it is missing.
+- [ ] Negative tests added where exceptions are expected.
+- [ ] Truth data added where simple `EXPECT_*` / `assert` checks are
+      insufficient for algorithmic correctness.
+- [ ] CI runtime impact considered; team notified if significant.
+
+### Documentation
+- [ ] Public-facing APIs have Doxygen docs.
+- [ ] User-visible behavior changes have public docs, or a follow-up is
+      tracked.
+- [ ] User-facing docs for new features are in a **separate PR** held until
+      release (the docs site publishes immediately on merge to the default
+      branch, so feature docs must not land before the feature ships).
+
+### Code style
+- [ ] Naming follows the existing convention (`snake_case` vs `camelCase`) for
+      the area being modified.
+
+### Dependencies
+- [ ] No new third-party dependencies, **or** the team has been notified and
+      OSRB tickets filed.

.github/actions/build-lib/action.yaml

@@ -1,4 +1,5 @@
 name: Build a CUDAQX library
+description: Configure, build, and optionally cache a CUDA-QX library
 
 inputs:
   lib:
@@ -21,7 +22,11 @@ inputs:
     required: true
   install-prefix:
     description: 'Install prefix'
-    default: '~/.cudaqx'
+    default: '$HOME/.cudaqx'
+    required: false
+  cudaq-prefix:
+    description: 'CUDA-Q install prefix'
+    default: '/cudaq-install'
     required: false
 outputs:
   build-dir:
@@ -67,7 +72,7 @@ runs:
         CCACHE_DIR: /ccache-${{ inputs.lib }}
       run: |
         build_dir=build_${{ inputs.lib }}
-        .github/actions/build-lib/build_${{ inputs.lib }}.sh $build_dir ${{ inputs.install-prefix }}
+        .github/actions/build-lib/build_${{ inputs.lib }}.sh "$build_dir" "${{ inputs.install-prefix }}" "${{ inputs.cudaq-prefix }}"
         echo "build_dir=$build_dir" >> $GITHUB_OUTPUT
       shell: bash
 
@@ -90,4 +95,3 @@ runs:
       with:
         path: /ccache-${{ inputs.lib }}
         key: ${{ steps.ccache-key.outputs.main }}${{ steps.ccache-key.outputs.pr }}
-

.github/actions/build-lib/build_all.sh

@@ -2,22 +2,26 @@
 
 . "$(dirname "$0")/setup_custabilizer.sh"
 
+build_dir=$1
+install_prefix=$2
+cudaq_prefix=$3
+
 _rt_flag=""
 if [ -n "$CUDAQ_REALTIME_ROOT" ]; then
   _rt_flag="-DCUDAQ_REALTIME_ROOT=$CUDAQ_REALTIME_ROOT"
 fi
 
-cmake -S . -B "$1" \
+cmake -S . -B "$build_dir" \
   -DCMAKE_BUILD_TYPE=Release \
   -DCMAKE_C_COMPILER=gcc-12 \
   -DCMAKE_CXX_COMPILER=g++-12 \
   -DCMAKE_C_COMPILER_LAUNCHER=ccache \
   -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-  -DCUDAQ_DIR=/cudaq-install/lib/cmake/cudaq/ \
+  -DCUDAQ_DIR="$cudaq_prefix/lib/cmake/cudaq/" \
   -DCUDAQX_ENABLE_LIBS="all" \
   -DCUDAQX_INCLUDE_TESTS=ON \
   -DCUDAQX_BINDINGS_PYTHON=ON \
-  -DCMAKE_INSTALL_PREFIX="$2" \
+  -DCMAKE_INSTALL_PREFIX="$install_prefix" \
   $_rt_flag
 
-cmake --build "$1" --target install -j 4
+cmake --build "$build_dir" --target install -j 4

.github/actions/build-lib/build_qec.sh

@@ -3,6 +3,10 @@ set -e
 
 . "$(dirname "$0")/setup_custabilizer.sh"
 
+build_dir=$1
+install_prefix=$2
+cudaq_prefix=$3
+
 # Build cuda-quantum realtime library + hololink tools (if CUDAQ_REALTIME_ROOT not set)
 if [ -z "$CUDAQ_REALTIME_ROOT" ]; then
   CUDAQ_REALTIME_ROOT=/tmp/cudaq-realtime
@@ -113,19 +117,19 @@ fi
 HSB_ROOT=/tmp/holoscan-sensor-bridge
 HSB_BUILD=${HSB_ROOT}/build
 
-cmake -S libs/qec -B "$1" \
+cmake -S libs/qec -B "$build_dir" \
   -DCMAKE_BUILD_TYPE=Release \
   -DCMAKE_C_COMPILER=gcc-12 \
   -DCMAKE_CXX_COMPILER=g++-12 \
   -DCMAKE_C_COMPILER_LAUNCHER=ccache \
   -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-  -DCUDAQ_DIR=/cudaq-install/lib/cmake/cudaq/ \
+  -DCUDAQ_DIR="$cudaq_prefix/lib/cmake/cudaq/" \
   -DCUDAQX_INCLUDE_TESTS=ON \
   -DCUDAQX_BINDINGS_PYTHON=ON \
-  -DCMAKE_INSTALL_PREFIX="$2" \
+  -DCMAKE_INSTALL_PREFIX="$install_prefix" \
   -DCUDAQ_REALTIME_ROOT=$CUDAQ_REALTIME_ROOT \
   -DCUDAQX_QEC_ENABLE_HOLOLINK_TOOLS=ON \
   -DHOLOSCAN_SENSOR_BRIDGE_SOURCE_DIR=$HSB_ROOT \
   -DHOLOSCAN_SENSOR_BRIDGE_BUILD_DIR=$HSB_BUILD
 
-cmake --build "$1" --target install -j 4
+cmake --build "$build_dir" --target install -j 4

.github/actions/build-lib/build_solvers.sh

@@ -1,14 +1,18 @@
 #!/bin/sh
 
-cmake -S libs/solvers -B "$1" \
+build_dir=$1
+install_prefix=$2
+cudaq_prefix=$3
+
+cmake -S libs/solvers -B "$build_dir" \
   -DCMAKE_BUILD_TYPE=Release \
   -DCMAKE_C_COMPILER=gcc-12 \
   -DCMAKE_CXX_COMPILER=g++-12 \
   -DCMAKE_C_COMPILER_LAUNCHER=ccache \
   -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-  -DCUDAQ_DIR=/cudaq-install/lib/cmake/cudaq/ \
+  -DCUDAQ_DIR="$cudaq_prefix/lib/cmake/cudaq/" \
   -DCUDAQX_INCLUDE_TESTS=ON \
   -DCUDAQX_BINDINGS_PYTHON=ON \
-  -DCMAKE_INSTALL_PREFIX="$2"
+  -DCMAKE_INSTALL_PREFIX="$install_prefix"
 
-cmake --build "$1" --target install -j 4
+cmake --build "$build_dir" --target install -j 4

.github/workflows/all_libs.yaml

@@ -16,6 +16,7 @@ jobs:
     container: ghcr.io/nvidia/cuda-quantum-devcontainer:${{ matrix.platform }}-cu${{ matrix.cuda_version }}-gcc12-main
     permissions:
       actions: write
+      contents: read
       pull-requests: read
     steps:
       - name: Checkout repository
@@ -113,7 +114,7 @@ jobs:
           # Install the correct torch first.
           cuda_no_dot=$(echo ${{ matrix.cuda_version }} | sed 's/\.//')
           pip install torch==2.9.0 --index-url https://download.pytorch.org/whl/cu${cuda_no_dot}
-          pip install numpy pytest onnxscript cuquantum-cu${{ steps.config.outputs.cuda_major }} lightning ml_collections mpi4py transformers quimb opt_einsum nvidia-cublas "cuquantum-python-cu${{ steps.config.outputs.cuda_major }}>=26.3.0"
+          pip install numpy pytest onnxscript cuquantum-cu${{ steps.config.outputs.cuda_major }} lightning ml_collections mpi4py transformers quimb opt_einsum cotengra nvidia-cublas "cuquantum-python-cu${{ steps.config.outputs.cuda_major }}>=26.3.0"
           # The following tests are needed for docs/sphinx/examples/qec/python/tensor_network_decoder.py.
           if [ "$(uname -m)" == "x86_64" ]; then
               # Stim is not currently available on manylinux ARM wheels, so only

.github/workflows/all_libs_release.yaml

@@ -129,6 +129,7 @@ jobs:
           cuda_version: ${{ matrix.cuda_version }}
           platform: ${{ matrix.runner.arch }}
           install-prefix: /usr/local/cudaq
+          cudaq-prefix: /usr/local/cudaq
 
       - name: Save build artifacts
         run: |
@@ -161,7 +162,7 @@ jobs:
           # Install the correct torch first.
           cuda_no_dot=$(echo ${{ matrix.cuda_version }} | sed 's/\.//')
           pip install torch==2.9.0 --index-url https://download.pytorch.org/whl/cu${cuda_no_dot}
-          pip install numpy pytest onnxscript cuquantum-cu${{ steps.config.outputs.cuda_major }} lightning ml_collections mpi4py transformers quimb opt_einsum nvidia-cublas "cuquantum-python-cu${{ steps.config.outputs.cuda_major }}>=26.3.0"
+          pip install numpy pytest onnxscript cuquantum-cu${{ steps.config.outputs.cuda_major }} lightning ml_collections mpi4py transformers quimb opt_einsum cotengra nvidia-cublas "cuquantum-python-cu${{ steps.config.outputs.cuda_major }}>=26.3.0"
           # The following tests are needed for docs/sphinx/examples/qec/python/tensor_network_decoder.py.
           if [ "$(uname -m)" == "x86_64" ]; then
               # Stim is not currently available on manylinux ARM wheels, so only
@@ -193,4 +194,3 @@ jobs:
         run: |
           ln -s /usr/local/cudaq /cudaq-install
           bash scripts/ci/test_examples.sh all 
-

.github/workflows/build_wheels.yaml

@@ -36,6 +36,31 @@ on:
         type: string
         description: Optional argument to take artifacts from a prior run of this workflow; facilitates rerunning a failed workflow without re-building the artifacts.
         required: false
+  workflow_call:
+    inputs:
+      build_type:
+        type: string
+        default: 'Release'
+        required: false
+      version:
+        type: string
+        required: false
+      cudaq_wheels:
+        type: string
+        default: 'Custom'
+        required: false
+      assets_repo:
+        type: string
+        default: ''
+        required: false
+      assets_tag:
+        type: string
+        default: ''
+        required: false
+      artifacts_from_run:
+        type: string
+        default: ''
+        required: false
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -129,7 +154,7 @@ jobs:
           bash .github/workflows/scripts/install_git_cli.sh
           if [[ -n "${{ inputs.assets_repo }}" ]] && [[ -n "${{ inputs.assets_tag }}" ]]; then
             # Fetch the assets into this directory
-            gh release download -R ${{ inputs.assets_repo }} ${{ inputs.assets_tag }}
+            gh release download -R "${{ inputs.assets_repo }}" "${{ inputs.assets_tag }}"
             ls
           fi
 
@@ -340,6 +365,7 @@ jobs:
           github-token: ${{ inputs.artifacts_from_run && secrets.WORKFLOW_TOKEN || github.token }}
 
       - name: Test wheels
+        shell: bash
         run: |
           # If using Custom CUDA-Q wheels, then /cudaq-wheels will exist.
           # Otherwise, the directory will not exist, and that is ok.
@@ -456,6 +482,7 @@ jobs:
           github-token: ${{ inputs.artifacts_from_run && secrets.WORKFLOW_TOKEN || github.token }}
 
       - name: Test wheels
+        shell: bash
         run: |
           # If using Custom CUDA-Q wheels, then /cudaq-wheels will exist.
           # Otherwise, the directory will not exist, and that is ok.