Pulling 0.10.0 release related things into main

.github/workflows/config/gitlab_commits.txt

@@ -1,2 +1,2 @@
 nvidia-mgpu-repo: cuda-quantum/cuquantum-mgpu.git
-nvidia-mgpu-commit: de32bf2abae42f118a0da36be0066296d76b0dbc
+nvidia-mgpu-commit: ddfaacf2ffd7dc1a9a4333e06474b213887d437c

.github/workflows/docker_images.yml

@@ -165,7 +165,7 @@ jobs:
           driver-opts: |
             network=host
             image=moby/buildkit:v0.19.0
-
+   
       - name: Build Open MPI
         id: docker_build
         uses: docker/build-push-action@v5
@@ -483,6 +483,9 @@ jobs:
 
           platform_tag=${{ needs.metadata.outputs.platform_tag }}
           cuda_major=`echo ${{ inputs.cuda_version }} | cut -d . -f1`
+          if [ "$cuda_major" == "11" ]; then
+            deprecation_notice="**Note**: Support for CUDA 11 will be removed in future releases. Please update to CUDA 12."
+          fi
           image_tag=${platform_tag:+$platform_tag-}${cuda_major:+cu${cuda_major}-}
           if ${{ github.event.pull_request.number != '' }} || [ -n "$(echo ${{ github.ref_name }} | grep pull-request/)" ]; then
             pr_number=`echo ${{ github.ref_name }} | grep -o [0-9]*`
@@ -502,6 +505,7 @@ jobs:
           echo "base_image=$base_image" >> $GITHUB_OUTPUT
           echo "devdeps_image=$devdeps_image" >> $GITHUB_OUTPUT
           echo "dev_image_name=$dev_image_name" >> $GITHUB_OUTPUT
+          echo "deprecation_notice=$deprecation_notice" >> $GITHUB_OUTPUT
 
           if ${{ inputs.environment == '' }}; then
             tar_archive=/tmp/cuda-quantum.tar
@@ -602,6 +606,7 @@ jobs:
             cudaqdev_image=${{ steps.prereqs.outputs.dev_image_name }}@${{ steps.release_build.outputs.digest }}
             base_image=${{ steps.prereqs.outputs.base_image }}
             release_version=${{ steps.prereqs.outputs.image_tag }}
+            deprecation_notice=${{ steps.prereqs.outputs.deprecation_notice }}
           tags: ${{ steps.cudaq_metadata.outputs.tags }}
           labels: ${{ steps.cudaq_metadata.outputs.labels }}
           platforms: ${{ inputs.platforms }}
@@ -719,7 +724,7 @@ jobs:
           # Unfortunately, we need to install cuquantum for docs generation to work properly, 
           # since using mock imports in the autodocs configuration doesn't work properly. 
           # See also https://github.com/sphinx-doc/sphinx/issues/11211. 
-          docker exec cuda-quantum-dev bash -c "python3 -m pip install cuquantum-python-cu12~=24.11"
+          docker exec cuda-quantum-dev bash -c "python3 -m pip install cuquantum-python-cu12~=25.03"
 
           (docker exec cuda-quantum-dev bash -c "export $docs_version && bash scripts/build_docs.sh" && built=true) || built=false
           if $built; then docker cp cuda-quantum-dev:"/usr/local/cudaq/docs/." docs; \

.github/workflows/publishing.yml

@@ -682,7 +682,7 @@ jobs:
           echo "docker_output=type=local,dest=/tmp/wheels" >> $GITHUB_OUTPUT
         env:
           GH_TOKEN: ${{ secrets.REPO_BOT_ACCESS_TOKEN }}
-      
+
       - name: Log in to DockerHub
         uses: docker/login-action@v3
         with:
@@ -1127,7 +1127,7 @@ jobs:
           pattern: '*-wheels'
           path: /tmp/wheels
           merge-multiple: true
-
+      
       - name: Load metapackage
         uses: actions/download-artifact@v4
         with:
@@ -1214,10 +1214,16 @@ jobs:
           for installer in `find installers/ -type f -not -name '*.whl'`; do 
             mv -v "$installer" "$(basename -- "$installer")"
           done
-          for dir in `ls wheelhouse/`; do 
-            mv -v "wheelhouse/$dir"/* wheelhouse/ && rmdir "wheelhouse/$dir"
+          # A single wheelhouse.zip file is too big. Split it up by platform.
+          platforms=$(ls wheelhouse | cut -d- -f1 | sort | uniq)
+          for p in $platforms; do
+            mkdir wheelhouse-${p}
+            for fulldir in wheelhouse/${p}-*; do
+              dir=$(basename $fulldir)
+              mv -v "wheelhouse/$dir"/* wheelhouse-${p}/ && rmdir "wheelhouse/$dir"
+            done
+            zip -r wheelhouse-${p}.zip wheelhouse-${p}
           done
-          zip -r wheelhouse.zip wheelhouse
           zip -r metapackages.zip metapackages
 
           release_id=${{ inputs.assets_from_run || github.run_id }}
@@ -1234,7 +1240,7 @@ jobs:
             --target $github_commit --draft $prerelease \
             --generate-notes --notes-start-tag $latest_tag --notes "$rel_notes"
           gh release upload $release_id -R ${{ github.repository }} install_cuda_quantum* --clobber
-          gh release upload $release_id -R ${{ github.repository }} wheelhouse.zip --clobber
+          gh release upload $release_id -R ${{ github.repository }} wheelhouse-*.zip --clobber
           gh release upload $release_id -R ${{ github.repository }} metapackages.zip --clobber
           gh release edit $release_id -R ${{ github.repository }} \
             --title "$release_title" --tag $version $prerelease # --draft=false

.github/workflows/python_metapackages.yml

@@ -59,9 +59,10 @@ jobs:
             echo "Creating README.md for cudaq package"
             package_name=cudaq
             cuda_version_requirement="11.x (where x \>= 8) or 12.x"
-            cuda_version_conda=11.8.0 # only used as example in the install script
+            cuda_version_conda=12.4.0 # only used as example in the install script
+            deprecation_notice="**Note**: Support for CUDA 11 will be removed in future releases. Please update to CUDA 12."
             cat python/README.md.in > python/metapackages/README.md
-            for variable in package_name cuda_version_requirement cuda_version_conda; do
+            for variable in package_name cuda_version_requirement cuda_version_conda deprecation_notice; do
               sed -i "s/.{{[ ]*$variable[ ]*}}/${!variable}/g" python/metapackages/README.md
             done
             if [ -n "$(cat python/metapackages/README.md | grep -e '.{{.*}}')" ]; then 

docker/build/assets.Dockerfile

@@ -263,7 +263,7 @@ RUN gcc_packages=$(dnf list installed "gcc*" | sed '/Installed Packages/d' | cut
 
 ## [Python MLIR tests]
 RUN cd /cuda-quantum && source scripts/configure_build.sh && \
-    python3 -m pip install lit pytest scipy cuquantum-python-cu$(echo ${CUDA_VERSION} | cut -d . -f1)~=24.11 && \
+    python3 -m pip install lit pytest scipy cuquantum-python-cu$(echo ${CUDA_VERSION} | cut -d . -f1)~=25.03 && \
     "${LLVM_INSTALL_PREFIX}/bin/llvm-lit" -v _skbuild/python/tests/mlir \
         --param nvqpp_site_config=_skbuild/python/tests/mlir/lit.site.cfg.py
 # The other tests for the Python wheel are run post-installation.

docker/build/devdeps.ext.Dockerfile

@@ -164,7 +164,7 @@ ENV PATH="${CUDA_INSTALL_PREFIX}/lib64/:${CUDA_INSTALL_PREFIX}/bin:${PATH}"
 RUN apt-get update && apt-get install -y --no-install-recommends \
         python3 python3-pip && \
     apt-get autoremove -y && apt-get clean && rm -rf /var/lib/apt/lists/* && \
-    python3 -m pip install cuquantum-python-cu$(echo $CUDA_VERSION | cut -d . -f1)~=24.11 && \
+    python3 -m pip install cuquantum-python-cu$(echo $CUDA_VERSION | cut -d . -f1)~=25.03 && \
     if [ "$(python3 --version | grep -o [0-9\.]* | cut -d . -f -2)" != "3.10" ]; then \
         echo "expecting Python version 3.10"; \
     fi

docker/release/cudaq.Dockerfile

@@ -99,7 +99,9 @@ Version: ${CUDA_QUANTUM_VERSION}\n\n\
 Copyright (c) 2025 NVIDIA Corporation & Affiliates \n\
 All rights reserved.\n\n\
 To run a command as administrator (user `root`), use `sudo <command>`.\n"
-RUN echo -e "$COPYRIGHT_NOTICE" > "$CUDA_QUANTUM_PATH/Copyright.txt"
+ARG deprecation_notice=""
+RUN echo -e "$COPYRIGHT_NOTICE" > "$CUDA_QUANTUM_PATH/Copyright.txt" && \
+    echo -e "$deprecation_notice" >> "$CUDA_QUANTUM_PATH/Copyright.txt"
 RUN echo 'cat "$CUDA_QUANTUM_PATH/Copyright.txt"' > /etc/profile.d/welcome.sh
 
 # See also https://github.com/microsoft/vscode-remote-release/issues/4781

docker/release/cudaq.wheel.Dockerfile

@@ -52,7 +52,10 @@ RUN cd cuda-quantum && cat python/README.md.in > python/README.md && \
     package_name=cuda-quantum-cu$(echo ${CUDA_VERSION} | cut -d . -f1) && \
     cuda_version_requirement="\>= ${CUDA_VERSION}" && \
     cuda_version_conda=${CUDA_VERSION}.0 && \
-    for variable in package_name cuda_version_requirement cuda_version_conda; do \
+    if [ "${CUDA_VERSION#11.}" != "${CUDA_VERSION}" ]; then \
+        deprecation_notice="**Note**: Support for CUDA 11 will be removed in future releases. Please update to CUDA 12."; \
+    fi && \
+    for variable in package_name cuda_version_requirement cuda_version_conda deprecation_notice; do \
         sed -i "s/.{{[ ]*$variable[ ]*}}/${!variable}/g" python/README.md; \
     done && \
     if [ -n "$(cat python/README.md | grep -e '.{{.*}}')" ]; then \

docker/release/installer.Dockerfile

@@ -54,6 +54,17 @@ RUN source /cuda-quantum/scripts/configure_build.sh && \
     ## [<CUDAQuantumAssets]
 
 ## [Self-extracting Archive]
+ARG deprecation_notice=""
+RUN if [ -z "${deprecation_notice}" ] && [ "${CUDA_VERSION#11.}" != "${CUDA_VERSION}" ]; then \
+        deprecation_notice="**Note**: Support for CUDA 11 will be removed in future releases. Please update to CUDA 12."; \
+    fi && \
+    if [ -n "${deprecation_notice}" ]; then \
+        notice="deprecation_notice='"${deprecation_notice}"'" && \
+        key='expected_key="Enter any key to continue."' && \
+        # prompt and wait for confirmation if input and output is a terminal, print to error stream otherwise
+        prompt='if [ -t 0 ] && [ -t 1 ]; then while true; do read -p "$deprecation_notice $expected_key" -r choice < /dev/tty; case "$choice" in * ) break;; esac; done; else echo -e "\e[01;31m${deprecation_notice}\e[0m" >&2; fi' && \
+        echo "$notice" >> install.sh && echo "$key" >> install.sh && echo "$prompt" >> install.sh; \
+    fi
 RUN bash /makeself/makeself.sh --gzip --sha256 --license /cuda-quantum/LICENSE \
         /cuda_quantum_assets install_cuda_quantum_cu$(echo ${CUDA_VERSION} | cut -d . -f1).$(uname -m) \
         "CUDA-Q toolkit for heterogeneous quantum-classical workflows" \

docs/sphinx/snippets/cpp/using/backends/trajectory_batching.cpp

@@ -0,0 +1,44 @@
+/*******************************************************************************
+ * Copyright (c) 2022 - 2025 NVIDIA Corporation & Affiliates.                  *
+ * All rights reserved.                                                        *
+ *                                                                             *
+ * This source code and the accompanying materials are made available under    *
+ * the terms of the Apache License 2.0 which accompanies this distribution.    *
+ ******************************************************************************/
+
+// [Begin Documentation]
+#include <chrono>
+#include <cudaq.h>
+#include <iostream>
+
+struct xOp {
+  void operator()(int qubit_count) __qpu__ {
+    cudaq::qvector q(qubit_count);
+    x(q);
+    mz(q);
+  }
+};
+
+int main() {
+  // Add a simple bit-flip noise channel to X gate
+  const double error_probability = 0.01;
+
+  cudaq::bit_flip_channel bit_flip(error_probability);
+  // Add noise channels to our noise model.
+  cudaq::noise_model noise_model;
+  // Apply the bitflip channel to any X-gate on any qubits
+  noise_model.add_all_qubit_channel<cudaq::types::x>(bit_flip);
+
+  const int qubit_count = 10;
+  const auto start_time = std::chrono::high_resolution_clock::now();
+  // Due to the impact of noise, our measurements will no longer be uniformly in
+  // the |1...1> state.
+  auto counts =
+      cudaq::sample({.shots = 1000, .noise = noise_model}, xOp{}, qubit_count);
+  const auto end_time = std::chrono::high_resolution_clock::now();
+  counts.dump();
+  const std::chrono::duration<double, std::milli> elapsed_time =
+      end_time - start_time;
+  std::cout << "Simulation elapsed time: " << elapsed_time.count() << "ms\n";
+  return 0;
+}

docs/sphinx/snippets/python/using/backends/trajectory.py

@@ -10,6 +10,9 @@
 import cudaq
 
 # Use the `nvidia` target
+# Other targets capable of trajectory simulation are:
+# - `tensornet`
+# - `tensornet-mps`
 cudaq.set_target("nvidia")
 
 # Let's define a simple kernel that we will add noise to.

docs/sphinx/snippets/python/using/backends/trajectory_batching.py

@@ -0,0 +1,46 @@
+# ============================================================================ #
+# Copyright (c) 2022 - 2024 NVIDIA Corporation & Affiliates.                   #
+# All rights reserved.                                                         #
+#                                                                              #
+# This source code and the accompanying materials are made available under     #
+# the terms of the Apache License 2.0 which accompanies this distribution.     #
+# ============================================================================ #
+
+#[Begin Docs]
+import time
+import cudaq
+# Use the `nvidia` target
+cudaq.set_target("nvidia")
+
+# Let's define a simple kernel that we will add noise to.
+qubit_count = 10
+
+
+@cudaq.kernel
+def kernel(qubit_count: int):
+    qvector = cudaq.qvector(qubit_count)
+    x(qvector)
+    mz(qvector)
+
+
+# Add a simple bit-flip noise channel to X gate
+error_probability = 0.01
+bit_flip = cudaq.BitFlipChannel(error_probability)
+
+# Add noise channels to our noise model.
+noise_model = cudaq.NoiseModel()
+# Apply the bit-flip channel to any X-gate on any qubits
+noise_model.add_all_qubit_channel("x", bit_flip)
+
+ideal_counts = cudaq.sample(kernel, qubit_count, shots_count=1000)
+
+start = time.time()
+# Due to the impact of noise, our measurements will no longer be uniformly
+# in the |1...1> state.
+noisy_counts = cudaq.sample(kernel,
+                            qubit_count,
+                            noise_model=noise_model,
+                            shots_count=1000)
+end = time.time()
+noisy_counts.dump()
+print(f"Simulation elapsed time: {(end - start) * 1000} ms")

docs/sphinx/snippets/python/using/backends/trajectory_observe.py

@@ -11,6 +11,9 @@
 from cudaq import spin
 
 # Use the `nvidia` target
+# Other targets capable of trajectory simulation are:
+# - `tensornet`
+# - `tensornet-mps`
 cudaq.set_target("nvidia")