From 437d81b65e840c3721daf73acec72e25241d6893 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Tue, 18 Jun 2024 16:20:14 -0400
Subject: [PATCH 01/16] Update determine runner workflow to use large runners
 if the branch name matches a certain format

---
 .github/workflows/determine-workflow-runner.yml | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index 78919a9762..edb865324c 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -33,8 +33,10 @@ jobs:
         if: >-
           ${{
             github.event_name == 'pull_request'
-            && contains(github.event.pull_request.labels.*.name, 'urgent')
             && startsWith(inputs.default_runner, 'ubuntu')
           }}
         id: runner_group
-        run: echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
\ No newline at end of file
+        run: |
+          if [[ ${{ contains(github.event.pull_request.labels.*.name, 'urgent') }} == 'true' || "${{ github.ref }}" =~ refs\/heads\/v\d+\.\d+\.\d+-rc\d? ]]; then
+            echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
+          fi

From bdd1a37cd53cfa4658d83f74a3857e445d3f20c7 Mon Sep 17 00:00:00 2001
From: ringo-but-quantum <github-ringo-but-quantum@xanadu.ai>
Date: Tue, 18 Jun 2024 20:21:35 +0000
Subject: [PATCH 02/16] Auto update version from '0.37.0-dev42' to
 '0.37.0-dev43'

---
 pennylane_lightning/core/_version.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pennylane_lightning/core/_version.py b/pennylane_lightning/core/_version.py
index d9e5793cb2..054ae191d1 100644
--- a/pennylane_lightning/core/_version.py
+++ b/pennylane_lightning/core/_version.py
@@ -16,4 +16,4 @@
    Version number (major.minor.patch[-label])
 """
 
-__version__ = "0.37.0-dev42"
+__version__ = "0.37.0-dev43"

From e94e0b22e171ff8f2c1dc5c73aa90af2a422b4c8 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Tue, 18 Jun 2024 16:25:50 -0400
Subject: [PATCH 03/16] Change parameter to use head_ref

---
 .github/workflows/determine-workflow-runner.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index edb865324c..5701079545 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -37,6 +37,6 @@ jobs:
           }}
         id: runner_group
         run: |
-          if [[ ${{ contains(github.event.pull_request.labels.*.name, 'urgent') }} == 'true' || "${{ github.ref }}" =~ refs\/heads\/v\d+\.\d+\.\d+-rc\d? ]]; then
+          if [[ ${{ contains(github.event.pull_request.labels.*.name, 'urgent') }} == 'true' || "${{ github.head_ref }}" =~ refs\/heads\/v\d+\.\d+\.\d+-rc\d? ]]; then
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
           fi

From cf2b19e9eda32c864211be6aa7f55c2e10326868 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Tue, 18 Jun 2024 16:30:12 -0400
Subject: [PATCH 04/16] Use head.ref from pr context

---
 .github/workflows/determine-workflow-runner.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index 5701079545..5441cccc7a 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -37,6 +37,6 @@ jobs:
           }}
         id: runner_group
         run: |
-          if [[ ${{ contains(github.event.pull_request.labels.*.name, 'urgent') }} == 'true' || "${{ github.head_ref }}" =~ refs\/heads\/v\d+\.\d+\.\d+-rc\d? ]]; then
+          if [[ ${{ contains(github.event.pull_request.labels.*.name, 'urgent') }} == 'true' || "${{ github.event.pull_request.head.ref }}" =~ refs\/heads\/v\d+\.\d+\.\d+-rc\d? ]]; then
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
           fi

From 8027b632a37900c88404ea787925ba654078d39b Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Tue, 18 Jun 2024 16:33:09 -0400
Subject: [PATCH 05/16] Don't use branch name for large runner if forked PR

---
 .github/workflows/determine-workflow-runner.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index 5441cccc7a..a0252980bf 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -37,6 +37,6 @@ jobs:
           }}
         id: runner_group
         run: |
-          if [[ ${{ contains(github.event.pull_request.labels.*.name, 'urgent') }} == 'true' || "${{ github.event.pull_request.head.ref }}" =~ refs\/heads\/v\d+\.\d+\.\d+-rc\d? ]]; then
+          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name == 'PennyLaneAI/pennylane-lightning' }}' == 'true' && "${{ github.event.pull_request.head.ref }}" =~ v\d+\.\d+\.\d+-rc\d?) ]]; then
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
           fi

From d817eedbf922ec8a6b85f5aa922dca87402fd632 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Wed, 19 Jun 2024 10:49:46 -0400
Subject: [PATCH 06/16] Fix regex

---
 .github/workflows/determine-workflow-runner.yml | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index a0252980bf..4bb994275f 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -36,7 +36,11 @@ jobs:
             && startsWith(inputs.default_runner, 'ubuntu')
           }}
         id: runner_group
+        env:
+          # We are not able to use \d to check numeric values as bash does not allow them (not POSIX compliant)
+          RC_BRANCH_FORMAT_REGEX: v[0-9]+\.[0-9]+\.[0-9]+-rc[0-9]?
+          REPO_FULL_NAME: PennyLaneAI/pennylane-lightning
         run: |
-          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name == 'PennyLaneAI/pennylane-lightning' }}' == 'true' && "${{ github.event.pull_request.head.ref }}" =~ v\d+\.\d+\.\d+-rc\d?) ]]; then
+          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && "${{ github.event.pull_request.head.ref }}" =~ "$RC_BRANCH_FORMAT_REGEX") ]]; then
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
           fi

From ccabde6c27909ec78b2aadcdcbe742f1fc78a050 Mon Sep 17 00:00:00 2001
From: ringo-but-quantum <github-ringo-but-quantum@xanadu.ai>
Date: Wed, 19 Jun 2024 14:50:20 +0000
Subject: [PATCH 07/16] Auto update version from '0.37.0-dev43' to
 '0.37.0-dev44'

---
 pennylane_lightning/core/_version.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pennylane_lightning/core/_version.py b/pennylane_lightning/core/_version.py
index 054ae191d1..46f1c1e8ff 100644
--- a/pennylane_lightning/core/_version.py
+++ b/pennylane_lightning/core/_version.py
@@ -16,4 +16,4 @@
    Version number (major.minor.patch[-label])
 """
 
-__version__ = "0.37.0-dev43"
+__version__ = "0.37.0-dev44"

From 544a07fad0d45cc09dc070e954c6f39a6db620c5 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Wed, 19 Jun 2024 12:18:12 -0400
Subject: [PATCH 08/16] Trigger CI


From 48e2df1aa0f10cd2c66912ad51262214d5e6fae2 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Wed, 19 Jun 2024 12:18:20 -0400
Subject: [PATCH 09/16] Trigger CI


From 1672f4c6aef443c51b6ac18fb5c7572600247cdc Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Wed, 19 Jun 2024 14:11:40 -0400
Subject: [PATCH 10/16] Update changelog

---
 .github/CHANGELOG.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.github/CHANGELOG.md b/.github/CHANGELOG.md
index 9fe7cf5066..61db240bb6 100644
--- a/.github/CHANGELOG.md
+++ b/.github/CHANGELOG.md
@@ -35,6 +35,8 @@
 
 ### Improvements
 
+* Release candidate branches are automatically switched over to using the new large GitHub runner pool [(#769)](https://github.com/PennyLaneAI/pennylane-lightning/pull/769)
+
 * LightningKokkos dev wheels for MacOS (x86_64, ARM64) and Linux (aarch64) are uploaded to TestPyPI upon PR merge.
   [(#765)](https://github.com/PennyLaneAI/pennylane-lightning/pull/765)
 

From 2d967a84bf95c7b89e580765369ec2022a1f4dd2 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Fri, 21 Jun 2024 12:25:42 -0400
Subject: [PATCH 11/16] Fix issue with regex check and added additional echo
 statements to show progress

---
 .github/workflows/determine-workflow-runner.yml | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index 4bb994275f..bd2d0b4afc 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -41,6 +41,9 @@ jobs:
           RC_BRANCH_FORMAT_REGEX: v[0-9]+\.[0-9]+\.[0-9]+-rc[0-9]?
           REPO_FULL_NAME: PennyLaneAI/pennylane-lightning
         run: |
-          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && "${{ github.event.pull_request.head.ref }}" =~ "$RC_BRANCH_FORMAT_REGEX") ]]; then
+          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && "${{ github.event.pull_request.head.ref }}" =~ $RC_BRANCH_FORMAT_REGEX) ]]; then
+            echo "This job requires usage of the large runner group '$LARGE_RUNNER_GROUP_NAME'";
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "This job does not require usage of large runners ...";
           fi

From b97e69fd20fe6c0be8d13e12ee830748fa1ec175 Mon Sep 17 00:00:00 2001
From: ringo-but-quantum <github-ringo-but-quantum@xanadu.ai>
Date: Fri, 21 Jun 2024 16:34:56 +0000
Subject: [PATCH 12/16] Auto update version from '0.37.0-dev45' to
 '0.37.0-dev46'

---
 pennylane_lightning/core/_version.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pennylane_lightning/core/_version.py b/pennylane_lightning/core/_version.py
index f288d1200e..8a46df66d0 100644
--- a/pennylane_lightning/core/_version.py
+++ b/pennylane_lightning/core/_version.py
@@ -16,4 +16,4 @@
    Version number (major.minor.patch[-label])
 """
 
-__version__ = "0.37.0-dev45"
+__version__ = "0.37.0-dev46"

From 51638cbb0056c786637c3c8b43973efdcea5d763 Mon Sep 17 00:00:00 2001
From: Vincent Michaud-Rioux <vincentm@nanoacademic.com>
Date: Thu, 20 Jun 2024 15:26:56 -0400
Subject: [PATCH 13/16] Fix bug in large runner determination workflow

Fix issue with regex check and added additional echo statements to show progress
---
 .github/CHANGELOG.md                          |   1 +
 .../workflows/determine-workflow-runner.yml   |   5 +-
 .github/workflows/docker_linux_x86_64.yml     |   4 +-
 Makefile                                      |   2 +-
 docker/Dockerfile                             | 123 +++---------
 pennylane_lightning/core/_version.py          |   2 +-
 .../gates/BasicGateFunctors.hpp               | 179 +++++++++++-------
 .../gates/BasicGeneratorFunctors.hpp          | 115 ++++++-----
 8 files changed, 216 insertions(+), 215 deletions(-)

diff --git a/.github/CHANGELOG.md b/.github/CHANGELOG.md
index 871b50c2d0..4e7b73b709 100644
--- a/.github/CHANGELOG.md
+++ b/.github/CHANGELOG.md
@@ -35,6 +35,7 @@
 
 ### Improvements
 
+
 * Release candidate branches are automatically switched over to using the new large GitHub runner pool.
   [(#769)](https://github.com/PennyLaneAI/pennylane-lightning/pull/769)
 
diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index 4bb994275f..bd2d0b4afc 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -41,6 +41,9 @@ jobs:
           RC_BRANCH_FORMAT_REGEX: v[0-9]+\.[0-9]+\.[0-9]+-rc[0-9]?
           REPO_FULL_NAME: PennyLaneAI/pennylane-lightning
         run: |
-          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && "${{ github.event.pull_request.head.ref }}" =~ "$RC_BRANCH_FORMAT_REGEX") ]]; then
+          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && "${{ github.event.pull_request.head.ref }}" =~ $RC_BRANCH_FORMAT_REGEX) ]]; then
+            echo "This job requires usage of the large runner group '$LARGE_RUNNER_GROUP_NAME'";
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "This job does not require usage of large runners ...";
           fi
diff --git a/.github/workflows/docker_linux_x86_64.yml b/.github/workflows/docker_linux_x86_64.yml
index 77b315f7bc..e3a622903e 100644
--- a/.github/workflows/docker_linux_x86_64.yml
+++ b/.github/workflows/docker_linux_x86_64.yml
@@ -12,7 +12,7 @@ on:
       lightning-version:
         type: string
         required: true
-        description: The version of Lightning to use. This should be a valid semantic version, e.g. 0.34.0.
+        description: The version of Lightning to use. This should be a valid git tag, e.g. v0.36.0.
       push-to-dockerhub:
         type: boolean
         required: true
@@ -22,7 +22,7 @@ on:
       lightning-version:
         type: string
         required: true
-        description: The version of Lightning to use. This should be a valid semantic version, e.g. 0.34.0.
+        description: The version of Lightning to use. This should be a valid git tag, e.g. v0.36.0.
       push-to-dockerhub:
         type: boolean
         required: true
diff --git a/Makefile b/Makefile
index 3d40597db9..55bf7b55a5 100644
--- a/Makefile
+++ b/Makefile
@@ -150,7 +150,7 @@ endif
 ifdef version
     VERSION := $(version)
 else
-    VERSION := v0.35.0
+    VERSION := v0.36.0
 endif
 
 docker-build:
diff --git a/docker/Dockerfile b/docker/Dockerfile
index cec4284bef..33b1139457 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -16,17 +16,19 @@
 # Define build arguments
 # Create and activate runtime virtual environment
 FROM ubuntu:jammy AS base-runtime
-ARG AMD_ARCH=AMD_GFX90A
 ARG CUDA_ARCH=AMPERE80
+ARG AMD_ARCH=AMD_GFX90A
 ARG CUDA_INSTALLER=https://developer.download.nvidia.com/compute/cuda/12.2.2/local_installers/cuda_12.2.2_535.104.05_linux.run
+ARG DEBIAN_FRONTEND=noninteractive
 ARG GCC_VERSION=11
-ARG KOKKOS_VERSION=4.3.01
 ARG LIGHTNING_VERSION=v0.36.0
-ARG ROCM_INSTALLER=https://repo.radeon.com/amdgpu-install/5.7/ubuntu/jammy/amdgpu-install_5.7.50700-1_all.deb
+ARG PENNYLANE_VERSION=v0.36.0
+ARG ROCM_INSTALLER=https://repo.radeon.com/amdgpu-install/6.1.1/ubuntu/jammy/amdgpu-install_6.1.60101-1_all.deb
 RUN apt-get update \
     && apt-get install --no-install-recommends -y \
     apt-utils \
     ca-certificates \
+    git \
     libgomp1 \
     python3 \
     python3-pip \
@@ -47,7 +49,6 @@ RUN apt-get update \
     ccache \
     cmake \
     curl \
-    git \
     ninja-build \
     python3-dev \
     gcc-${GCC_VERSION} g++-${GCC_VERSION} cpp-${GCC_VERSION} \
@@ -70,9 +71,7 @@ RUN python3 -m venv $VIRTUAL_ENV
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 RUN rm -rf tmp && git clone --depth 1 --branch ${LIGHTNING_VERSION} https://github.com/PennyLaneAI/pennylane-lightning.git tmp\
     && mv tmp/* /opt/pennylane-lightning && rm -rf tmp
-RUN pip install --no-cache-dir wheel
-RUN pip install --no-cache-dir -r requirements-dev.txt
-RUN pip install --no-cache-dir -r doc/requirements.txt
+RUN pip install --no-cache-dir cmake ninja pybind11 wheel
 
 # Download Lightning release and build lightning-qubit backend
 FROM base-build-python AS build-wheel-lightning-qubit
@@ -85,44 +84,22 @@ RUN python setup.py bdist_wheel
 FROM base-runtime AS wheel-lightning-qubit
 COPY --from=build-wheel-lightning-qubit /opt/pennylane-lightning/dist/ /
 RUN pip install --force-reinstall --no-cache-dir PennyLane_Lightning*.whl && rm PennyLane_Lightning*.whl
-RUN pip install --no-cache-dir -U pennylane
-
-# Download Kokkos release and build OpenMP backend
-FROM base-build as build-kokkos-openmp
-WORKDIR /opt/kokkos-${KOKKOS_VERSION}
-RUN wget --progress=dot:giga https://github.com/kokkos/kokkos/archive/refs/tags/${KOKKOS_VERSION}.tar.gz
-RUN tar -zxf ${KOKKOS_VERSION}.tar.gz && mv /opt/kokkos-${KOKKOS_VERSION}/kokkos-${KOKKOS_VERSION}/* /opt/kokkos-${KOKKOS_VERSION}
-RUN cmake -S /opt/kokkos-${KOKKOS_VERSION} -B /opt/kokkos-${KOKKOS_VERSION}/build \
-    -G Ninja \
-    -DCMAKE_BUILD_TYPE=Release \
-    -DCMAKE_INSTALL_PREFIX=/opt/kokkos \
-    -DBUILD_SHARED_LIBS:BOOL=ON \
-    -DBUILD_TESTING:BOOL=OFF \
-    -DKokkos_ENABLE_SERIAL:BOOL=ON \
-    -DKokkos_ENABLE_OPENMP:BOOL=ON \
-    -DCMAKE_CXX_STANDARD=20 \
-    -DKokkos_ENABLE_EXAMPLES:BOOL=OFF \
-    -DKokkos_ENABLE_TESTS:BOOL=OFF \
-    -DKokkos_ENABLE_LIBDL:BOOL=OFF
-RUN cmake --build /opt/kokkos-${KOKKOS_VERSION}/build
-RUN cmake --install /opt/kokkos-${KOKKOS_VERSION}/build
+RUN pip install --no-cache-dir git+https://github.com/PennyLaneAI/pennylane.git@${PENNYLANE_VERSION}
 
 # Download Lightning release and build lightning-kokkos backend with Kokkos-OpenMP
 FROM base-build-python AS build-wheel-lightning-kokkos-openmp
 WORKDIR /opt/pennylane-lightning
-COPY --from=build-kokkos-openmp /opt/kokkos /opt/kokkos
-ENV CMAKE_PREFIX_PATH=/opt/kokkos:$CMAKE_PREFIX_PATH
+ENV PL_BACKEND=lightning_kokkos
 RUN pip uninstall -y pennylane-lightning
-RUN PL_BACKEND=lightning_kokkos python setup.py build_ext
-RUN PL_BACKEND=lightning_kokkos python setup.py bdist_wheel
+RUN python setup.py build_ext -i --define="Kokkos_ENABLE_SERIAL:BOOL=ON;Kokkos_ENABLE_OPENMP:BOOL=ON"
+RUN python setup.py bdist_wheel
 
 # Install lightning-kokkos OpenMP backend
 FROM base-runtime AS wheel-lightning-kokkos-openmp
-COPY --from=build-kokkos-openmp /opt/kokkos /opt/kokkos
 COPY --from=build-wheel-lightning-kokkos-openmp /opt/pennylane-lightning/dist/ /
 COPY --from=build-wheel-lightning-qubit /opt/pennylane-lightning/dist/ /
 RUN pip install --force-reinstall --no-cache-dir PennyLane_Lightning*.whl && rm PennyLane_Lightning*.whl
-RUN pip install --no-cache-dir -U pennylane
+RUN pip install --no-cache-dir git+https://github.com/PennyLaneAI/pennylane.git@${PENNYLANE_VERSION}
 
 # Install CUDA-12 in build venv image
 FROM base-build-python as base-build-cuda
@@ -133,45 +110,23 @@ RUN ./cuda-install.run --silent --toolkit --toolkitpath=/usr/local/cuda-$(echo $
 ENV PATH=/usr/local/cuda/bin:${PATH}
 ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH}
 
-# Download Kokkos release and build CUDA backend
-FROM base-build-cuda as build-kokkos-cuda
-WORKDIR /opt/kokkos-${KOKKOS_VERSION}
-# RUN wget --progress=dot:giga https://github.com/kokkos/kokkos/archive/refs/tags/${KOKKOS_VERSION}.tar.gz
-# RUN tar -zxf ${KOKKOS_VERSION}.tar.gz && mv /opt/kokkos-${KOKKOS_VERSION}/kokkos-${KOKKOS_VERSION}/* /opt/kokkos-${KOKKOS_VERSION}
-RUN git clone --branch lightning https://github.com/vincentmr/kokkos.git /opt/kokkos-${KOKKOS_VERSION}
-RUN cmake -S /opt/kokkos-${KOKKOS_VERSION} -B /opt/kokkos-${KOKKOS_VERSION}/build \
-    -G Ninja \
-    -DCMAKE_BUILD_TYPE=Release \
-    -DCMAKE_INSTALL_PREFIX=/opt/kokkos \
-    -DBUILD_SHARED_LIBS:BOOL=ON \
-    -DBUILD_TESTING:BOOL=OFF \
-    -DKokkos_ENABLE_SERIAL:BOOL=ON \
-    -DKokkos_ENABLE_OPENMP:BOOL=ON \
-    -DCMAKE_CXX_STANDARD=20 \
-    -DKokkos_ENABLE_EXAMPLES:BOOL=OFF \
-    -DKokkos_ENABLE_TESTS:BOOL=OFF \
-    -DKokkos_ENABLE_LIBDL:BOOL=OFF \
-    -DKokkos_ENABLE_CUDA:BOOL=ON \
-    -DKokkos_ARCH_${CUDA_ARCH}=ON
-RUN cmake --build /opt/kokkos-${KOKKOS_VERSION}/build
-RUN cmake --install /opt/kokkos-${KOKKOS_VERSION}/build
-
 # Download Lightning release and build lightning-kokkos backend with Kokkos-CUDA
 FROM base-build-cuda AS build-wheel-lightning-kokkos-cuda
 WORKDIR /opt/pennylane-lightning
-COPY --from=build-kokkos-cuda /opt/kokkos /opt/kokkos
-ENV CMAKE_PREFIX_PATH=/opt/kokkos:$CMAKE_PREFIX_PATH
+ENV PL_BACKEND=lightning_kokkos
 RUN pip uninstall -y pennylane-lightning
 RUN echo >> cmake/support_kokkos.cmake && echo "find_package(CUDAToolkit REQUIRED)" >> cmake/support_kokkos.cmake
-RUN PL_BACKEND=lightning_kokkos python setup.py build_ext
-RUN PL_BACKEND=lightning_kokkos python setup.py bdist_wheel
+RUN python setup.py build_ext -i --define="Kokkos_ENABLE_SERIAL:BOOL=ON;Kokkos_ENABLE_OPENMP:BOOL=ON;Kokkos_ENABLE_CUDA:BOOL=ON;Kokkos_ARCH_${CUDA_ARCH}=ON"
+RUN python setup.py bdist_wheel
 
 # Install python3 and setup runtime virtual env in CUDA-12-runtime image (includes CUDA runtime and math libraries)
 # Install lightning-kokkos CUDA backend
 FROM nvidia/cuda:12.2.0-base-ubuntu22.04 AS wheel-lightning-kokkos-cuda
+ARG PENNYLANE_VERSION=v0.36.0
 RUN apt-get update \
     && apt-get install --no-install-recommends -y \
     libgomp1 \
+    git \
     python3 \
     python3-pip \
     python3-venv \
@@ -180,11 +135,10 @@ RUN apt-get update \
 ENV VIRTUAL_ENV=/opt/venv
 RUN python3 -m venv $VIRTUAL_ENV
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-COPY --from=build-kokkos-cuda /opt/kokkos /opt/kokkos
 COPY --from=build-wheel-lightning-kokkos-cuda /opt/pennylane-lightning/dist/ /
 COPY --from=build-wheel-lightning-qubit /opt/pennylane-lightning/dist/ /
 RUN pip install --force-reinstall --no-cache-dir PennyLane_Lightning*.whl && rm PennyLane_Lightning*.whl
-RUN pip install --no-cache-dir -U pennylane
+RUN pip install --no-cache-dir git+https://github.com/PennyLaneAI/pennylane.git@${PENNYLANE_VERSION}
 
 # Download and build Lightning-GPU release
 FROM base-build-cuda AS build-wheel-lightning-gpu
@@ -192,13 +146,15 @@ WORKDIR /opt/pennylane-lightning
 RUN pip install --no-cache-dir wheel custatevec-cu12
 RUN pip uninstall -y pennylane-lightning
 RUN CUQUANTUM_SDK=$(python -c "import site; print( f'{site.getsitepackages()[0]}/cuquantum/lib')") PL_BACKEND=lightning_gpu python setup.py build_ext
-RUN PL_BACKEND=lightning_gpu python setup.py bdist_wheel
+RUN python setup.py bdist_wheel
 
 # Install python3 and setup runtime virtual env in CUDA-12-runtime image (includes CUDA runtime and math libraries)
 # Install lightning-kokkos CUDA backend
 FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS wheel-lightning-gpu
+ARG PENNYLANE_VERSION=v0.36.0
 RUN apt-get update \
     && apt-get install --no-install-recommends -y \
+    git \
     libgomp1 \
     python3 \
     python3-pip \
@@ -213,7 +169,7 @@ ENV LD_LIBRARY_PATH="$VIRTUAL_ENV/lib/python3.10/site-packages/cuquantum/lib:$LD
 COPY --from=build-wheel-lightning-gpu /opt/pennylane-lightning/dist/ /
 COPY --from=build-wheel-lightning-qubit /opt/pennylane-lightning/dist/ /
 RUN pip install --no-cache-dir --force-reinstall PennyLane_Lightning*.whl && rm PennyLane_Lightning*.whl
-RUN pip install --no-cache-dir -U pennylane
+RUN pip install --no-cache-dir git+https://github.com/PennyLaneAI/pennylane.git@${PENNYLANE_VERSION}
 
 # Install ROCm in build venv image
 FROM base-build-python as base-build-rocm
@@ -226,44 +182,22 @@ RUN apt-get update \
     && rm -rf /var/lib/apt/lists/*
 RUN amdgpu-install -y --accept-eula --usecase=rocm,hiplibsdk --no-dkms
 
-# Download Kokkos release and build HIP backend
-FROM base-build-rocm as build-kokkos-rocm
-WORKDIR /opt/kokkos-${KOKKOS_VERSION}
-ENV LD_LIBRARY_PATH=/opt/rocm/lib:$LD_LIBRARY_PATH
-# RUN wget --progress=dot:giga https://github.com/kokkos/kokkos/archive/refs/tags/${KOKKOS_VERSION}.tar.gz
-# RUN tar -zxf ${KOKKOS_VERSION}.tar.gz && mv /opt/kokkos-${KOKKOS_VERSION}/kokkos-${KOKKOS_VERSION}/* /opt/kokkos-${KOKKOS_VERSION}
-RUN git clone --branch fix-rtld-deepbind https://github.com/cz4rs/kokkos.git /opt/kokkos-${KOKKOS_VERSION}
-RUN CXX=hipcc cmake -S /opt/kokkos-${KOKKOS_VERSION} -B /opt/kokkos-${KOKKOS_VERSION}/build \
-    -G Ninja \
-    -DCMAKE_BUILD_TYPE=Release \
-    -DCMAKE_INSTALL_PREFIX=/opt/kokkos \
-    -DBUILD_SHARED_LIBS:BOOL=ON \
-    -DBUILD_TESTING:BOOL=OFF \
-    -DKokkos_ENABLE_SERIAL:BOOL=ON \
-    -DKokkos_ENABLE_OPENMP:BOOL=ON \
-    -DCMAKE_CXX_STANDARD=20 \
-    -DKokkos_ENABLE_EXAMPLES:BOOL=OFF \
-    -DKokkos_ENABLE_TESTS:BOOL=OFF \
-    -DKokkos_ENABLE_LIBDL:BOOL=OFF \
-    -DKokkos_ENABLE_HIP:BOOL=ON \
-    -DKokkos_ARCH_${AMD_ARCH}=ON
-RUN cmake --build /opt/kokkos-${KOKKOS_VERSION}/build
-RUN cmake --install /opt/kokkos-${KOKKOS_VERSION}/build
-
 # Download Lightning release and build lightning-kokkos backend with Kokkos-ROCm
 FROM base-build-rocm AS build-wheel-lightning-kokkos-rocm
 WORKDIR /opt/pennylane-lightning
-COPY --from=build-kokkos-rocm /opt/kokkos /opt/kokkos
+ENV CMAKE_PREFIX_PATH=/opt/rocm:$CMAKE_PREFIX_PATH
 ENV CXX=hipcc
-ENV CMAKE_PREFIX_PATH=/opt/kokkos:$CMAKE_PREFIX_PATH
+ENV PL_BACKEND=lightning_kokkos
 RUN pip uninstall -y pennylane-lightning
-RUN PL_BACKEND=lightning_kokkos python setup.py build_ext
-RUN PL_BACKEND=lightning_kokkos python setup.py bdist_wheel
+RUN python setup.py build_ext -i --define="PL_BACKEND=lightning_kokkos;Kokkos_ENABLE_SERIAL:BOOL=ON;Kokkos_ENABLE_OPENMP:BOOL=ON;Kokkos_ENABLE_HIP:BOOL=ON;Kokkos_ARCH_${AMD_ARCH}=ON"
+RUN python setup.py bdist_wheel
 
 # Install lightning-kokkos HIP backend
 FROM rocm/dev-ubuntu-22.04:5.7 AS wheel-lightning-kokkos-rocm
+ARG PENNYLANE_VERSION=v0.36.0
 RUN apt-get update \
     && apt-get install --no-install-recommends -y \
+    git \
     libgomp1 \
     python3 \
     python3-pip \
@@ -273,8 +207,7 @@ RUN apt-get update \
 ENV VIRTUAL_ENV=/opt/venv
 RUN python3 -m venv $VIRTUAL_ENV
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-COPY --from=build-kokkos-rocm /opt/kokkos /opt/kokkos
 COPY --from=build-wheel-lightning-kokkos-rocm /opt/pennylane-lightning/dist/ /
 COPY --from=build-wheel-lightning-qubit /opt/pennylane-lightning/dist/ /
 RUN pip install --force-reinstall --no-cache-dir PennyLane_Lightning*.whl && rm PennyLane_Lightning*.whl
-RUN pip install --no-cache-dir -U pennylane
+RUN pip install --no-cache-dir git+https://github.com/PennyLaneAI/pennylane.git@${PENNYLANE_VERSION}
diff --git a/pennylane_lightning/core/_version.py b/pennylane_lightning/core/_version.py
index 46f1c1e8ff..f288d1200e 100644
--- a/pennylane_lightning/core/_version.py
+++ b/pennylane_lightning/core/_version.py
@@ -16,4 +16,4 @@
    Version number (major.minor.patch[-label])
 """
 
-__version__ = "0.37.0-dev44"
+__version__ = "0.37.0-dev45"
diff --git a/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGateFunctors.hpp b/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGateFunctors.hpp
index ff125469e4..c8fee3f66b 100644
--- a/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGateFunctors.hpp
+++ b/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGateFunctors.hpp
@@ -100,8 +100,10 @@ void applyPauliZ(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC1Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i0,
-                      const std::size_t i1) { arr(i1) *= -1.0; });
+                      const std::size_t i0, const std::size_t i1) {
+            [[maybe_unused]] const auto i0_ = i0;
+            arr(i1) *= -1.0;
+        });
 }
 
 template <class ExecutionSpace, class PrecisionT>
@@ -113,8 +115,8 @@ void applyHadamard(
     applyNC1Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i0,
-                      const std::size_t i1) {
+                      const std::size_t i0, const std::size_t i1) {
+            [[maybe_unused]] const auto i0_ = i0;
             const Kokkos::complex<PrecisionT> v0 = arr(i0);
             const Kokkos::complex<PrecisionT> v1 = arr(i1);
             arr(i0) = M_SQRT1_2 * v0 +
@@ -135,8 +137,10 @@ void applyS(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC1Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i0,
-                      const std::size_t i1) { arr(i1) *= shift; });
+                      const std::size_t i0, const std::size_t i1) {
+            [[maybe_unused]] const auto i0_ = i0;
+            arr(i1) *= shift;
+        });
 }
 
 template <class ExecutionSpace, class PrecisionT>
@@ -152,8 +156,10 @@ void applyT(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC1Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i0,
-                      const std::size_t i1) { arr(i1) *= shift; });
+                      const std::size_t i0, const std::size_t i1) {
+            [[maybe_unused]] const auto i0_ = i0;
+            arr(i1) *= shift;
+        });
 }
 
 template <class ExecutionSpace, class PrecisionT>
@@ -169,8 +175,10 @@ void applyPhaseShift(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC1Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i0,
-                      const std::size_t i1) { arr(i1) *= shift; });
+                      const std::size_t i0, const std::size_t i1) {
+            [[maybe_unused]] const auto i0_ = i0;
+            arr(i1) *= shift;
+        });
 }
 
 template <class ExecutionSpace, class PrecisionT>
@@ -315,9 +323,11 @@ void applyCNOT(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
+                      const std::size_t i00, const std::size_t i01,
                       const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
+
             kokkos_swap(arr(i10), arr(i11));
         });
 }
@@ -331,9 +341,10 @@ void applyCY(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
+                      const std::size_t i00, const std::size_t i01,
                       const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
             Kokkos::complex<PrecisionT> v10 = arr(i10);
             arr(i10) =
                 Kokkos::complex<PrecisionT>{imag(arr(i11)), -real(arr(i11))};
@@ -350,10 +361,13 @@ void applyCZ(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
-                      [[maybe_unused]] const std::size_t i10,
-                      const std::size_t i11) { arr(i11) *= -1; });
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
+            [[maybe_unused]] const auto i10_ = i10;
+            arr(i11) *= -1;
+        });
 }
 
 template <class ExecutionSpace, class PrecisionT>
@@ -365,9 +379,11 @@ void applySWAP(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      const std::size_t i01, const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i11_ = i11;
+
             kokkos_swap(arr(i10), arr(i01));
         });
 }
@@ -385,10 +401,13 @@ void applyControlledPhaseShift(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
-                      [[maybe_unused]] const std::size_t i10,
-                      const std::size_t i11) { arr(i11) *= s; });
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
+            [[maybe_unused]] const auto i10_ = i10;
+            arr(i11) *= s;
+        });
 }
 
 template <class ExecutionSpace, class PrecisionT>
@@ -403,9 +422,10 @@ void applyCRX(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
+                      const std::size_t i00, const std::size_t i01,
                       const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
             const Kokkos::complex<PrecisionT> v10 = arr(i10);
             const Kokkos::complex<PrecisionT> v11 = arr(i11);
             arr(i10) = Kokkos::complex<PrecisionT>{
@@ -426,9 +446,10 @@ void applyCRY(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
+                      const std::size_t i00, const std::size_t i01,
                       const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
             const Kokkos::complex<PrecisionT> v10 = arr(i10);
             const Kokkos::complex<PrecisionT> v11 = arr(i11);
             arr(i10) = c * v10 - s * v11;
@@ -450,9 +471,11 @@ void applyCRZ(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
+                      const std::size_t i00, const std::size_t i01,
                       const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
+
             arr(i10) *= shift_0;
             arr(i11) *= shift_1;
         });
@@ -476,9 +499,10 @@ void applyCRot(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      [[maybe_unused]] const std::size_t i01,
+                      const std::size_t i00, const std::size_t i01,
                       const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i01_ = i01;
             const Kokkos::complex<PrecisionT> v0 = arr(i10);
             const Kokkos::complex<PrecisionT> v1 = arr(i11);
             arr(i10) = mat_0b00 * v0 + mat_0b01 * v1;
@@ -620,9 +644,11 @@ void applySingleExcitation(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      const std::size_t i01, const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i11_ = i11;
+
             const Kokkos::complex<PrecisionT> v01 = arr(i01);
             const Kokkos::complex<PrecisionT> v10 = arr(i10);
             arr(i01) = cr * v01 - sj * v10;
@@ -672,9 +698,11 @@ void applySingleExcitationPlus(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      const std::size_t i01, const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i11_ = i11;
+
             const Kokkos::complex<PrecisionT> v01 = arr(i01);
             const Kokkos::complex<PrecisionT> v10 = arr(i10);
             arr(i00) *= e;
@@ -758,13 +786,17 @@ void applyCSWAP(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC3Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i000,
-                      [[maybe_unused]] const std::size_t i001,
-                      [[maybe_unused]] const std::size_t i010,
-                      [[maybe_unused]] const std::size_t i011,
-                      [[maybe_unused]] const std::size_t i100,
-                      const std::size_t i101, const std::size_t i110,
-                      [[maybe_unused]] const std::size_t i111) {
+                      const std::size_t i000, const std::size_t i001,
+                      const std::size_t i010, const std::size_t i011,
+                      const std::size_t i100, const std::size_t i101,
+                      const std::size_t i110, const std::size_t i111) {
+            [[maybe_unused]] const auto i000_ = i000;
+            [[maybe_unused]] const auto i001_ = i001;
+            [[maybe_unused]] const auto i010_ = i010;
+            [[maybe_unused]] const auto i011_ = i011;
+            [[maybe_unused]] const auto i100_ = i100;
+            [[maybe_unused]] const auto i111_ = i111;
+
             kokkos_swap(arr(i101), arr(i110));
         });
 }
@@ -778,13 +810,17 @@ void applyToffoli(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
     applyNC3Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i000,
-                      [[maybe_unused]] const std::size_t i001,
-                      [[maybe_unused]] const std::size_t i010,
-                      [[maybe_unused]] const std::size_t i011,
-                      [[maybe_unused]] const std::size_t i100,
-                      [[maybe_unused]] const std::size_t i101,
+                      const std::size_t i000, const std::size_t i001,
+                      const std::size_t i010, const std::size_t i011,
+                      const std::size_t i100, const std::size_t i101,
                       const std::size_t i110, const std::size_t i111) {
+            [[maybe_unused]] const auto i000_ = i000;
+            [[maybe_unused]] const auto i001_ = i001;
+            [[maybe_unused]] const auto i010_ = i010;
+            [[maybe_unused]] const auto i011_ = i011;
+            [[maybe_unused]] const auto i100_ = i100;
+            [[maybe_unused]] const auto i101_ = i101;
+
             kokkos_swap(arr(i111), arr(i110));
         });
 }
@@ -914,22 +950,29 @@ void applyDoubleExcitation(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
         (inverse) ? -std::sin(angle / 2) : std::sin(angle / 2);
     applyNC4Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
-        KOKKOS_LAMBDA(
-            Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-            [[maybe_unused]] const std::size_t i0000,
-            [[maybe_unused]] const std::size_t i0001,
-            [[maybe_unused]] const std::size_t i0010, const std::size_t i0011,
-            [[maybe_unused]] const std::size_t i0100,
-            [[maybe_unused]] const std::size_t i0101,
-            [[maybe_unused]] const std::size_t i0110,
-            [[maybe_unused]] const std::size_t i0111,
-            [[maybe_unused]] const std::size_t i1000,
-            [[maybe_unused]] const std::size_t i1001,
-            [[maybe_unused]] const std::size_t i1010,
-            [[maybe_unused]] const std::size_t i1011, const std::size_t i1100,
-            [[maybe_unused]] const std::size_t i1101,
-            [[maybe_unused]] const std::size_t i1110,
-            [[maybe_unused]] const std::size_t i1111) {
+        KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
+                      const std::size_t i0000, const std::size_t i0001,
+                      const std::size_t i0010, const std::size_t i0011,
+                      const std::size_t i0100, const std::size_t i0101,
+                      const std::size_t i0110, const std::size_t i0111,
+                      const std::size_t i1000, const std::size_t i1001,
+                      const std::size_t i1010, const std::size_t i1011,
+                      const std::size_t i1100, const std::size_t i1101,
+                      const std::size_t i1110, const std::size_t i1111) {
+            [[maybe_unused]] const auto i0000_ = i0000;
+            [[maybe_unused]] const auto i0001_ = i0001;
+            [[maybe_unused]] const auto i0010_ = i0010;
+            [[maybe_unused]] const auto i0100_ = i0100;
+            [[maybe_unused]] const auto i0101_ = i0101;
+            [[maybe_unused]] const auto i0110_ = i0110;
+            [[maybe_unused]] const auto i0111_ = i0111;
+            [[maybe_unused]] const auto i1000_ = i1000;
+            [[maybe_unused]] const auto i1001_ = i1001;
+            [[maybe_unused]] const auto i1010_ = i1010;
+            [[maybe_unused]] const auto i1011_ = i1011;
+            [[maybe_unused]] const auto i1101_ = i1101;
+            [[maybe_unused]] const auto i1110_ = i1110;
+            [[maybe_unused]] const auto i1111_ = i1111;
             const Kokkos::complex<PrecisionT> v3 = arr(i0011);
             const Kokkos::complex<PrecisionT> v12 = arr(i1100);
             arr(i0011) = cr * v3 - sj * v12;
diff --git a/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGeneratorFunctors.hpp b/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGeneratorFunctors.hpp
index 33a78aae74..af461e5b88 100644
--- a/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGeneratorFunctors.hpp
+++ b/pennylane_lightning/core/src/simulators/lightning_kokkos/gates/BasicGeneratorFunctors.hpp
@@ -39,8 +39,8 @@ void applyGenPhaseShift(
     applyNC1Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      const std::size_t i0,
-                      [[maybe_unused]] const std::size_t i1) {
+                      const std::size_t i0, const std::size_t i1) {
+            [[maybe_unused]] auto i1_ = i1;
             arr(i0) = 0.0;
         });
 }
@@ -55,8 +55,9 @@ void applyGenControlledPhaseShift(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
                       const std::size_t i00, const std::size_t i01,
-                      const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i11_ = i11;
+
             arr(i00) = 0.0;
             arr(i01) = 0.0;
             arr(i10) = 0.0;
@@ -110,8 +111,8 @@ void applyGenCRZ(Kokkos::View<Kokkos::complex<PrecisionT> *> arr_,
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
                       const std::size_t i00, const std::size_t i01,
-                      [[maybe_unused]] const std::size_t i10,
-                      const std::size_t i11) {
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i10_ = i10;
             arr(i00) = 0.0;
             arr(i01) = 0.0;
             arr(i11) *= -1;
@@ -178,9 +179,11 @@ void applyGenIsingZZ(
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      const std::size_t i01, const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i11_ = i11;
+
             arr(i10) *= -1;
             arr(i01) *= -1;
         });
@@ -214,9 +217,11 @@ void applyGenSingleExcitationMinus(
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      const std::size_t i01, const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i11_ = i11;
+
             arr(i01) *= Kokkos::complex<PrecisionT>{0.0, 1.0};
             arr(i10) *= Kokkos::complex<PrecisionT>{0.0, -1.0};
             kokkos_swap(arr(i10), arr(i01));
@@ -232,9 +237,11 @@ void applyGenSingleExcitationPlus(
     applyNC2Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
         KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-                      [[maybe_unused]] const std::size_t i00,
-                      const std::size_t i01, const std::size_t i10,
-                      [[maybe_unused]] const std::size_t i11) {
+                      const std::size_t i00, const std::size_t i01,
+                      const std::size_t i10, const std::size_t i11) {
+            [[maybe_unused]] const auto i00_ = i00;
+            [[maybe_unused]] const auto i11_ = i11;
+
             arr(i00) *= -1;
             arr(i01) *= Kokkos::complex<PrecisionT>{0.0, 1.0};
             arr(i10) *= Kokkos::complex<PrecisionT>{0.0, -1.0};
@@ -289,22 +296,29 @@ void applyGenDoubleExcitationMinus(
     [[maybe_unused]] const std::vector<PrecisionT> &params = {}) {
     applyNC4Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
-        KOKKOS_LAMBDA(
-            Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-            [[maybe_unused]] const std::size_t i0000,
-            [[maybe_unused]] const std::size_t i0001,
-            [[maybe_unused]] const std::size_t i0010, const std::size_t i0011,
-            [[maybe_unused]] const std::size_t i0100,
-            [[maybe_unused]] const std::size_t i0101,
-            [[maybe_unused]] const std::size_t i0110,
-            [[maybe_unused]] const std::size_t i0111,
-            [[maybe_unused]] const std::size_t i1000,
-            [[maybe_unused]] const std::size_t i1001,
-            [[maybe_unused]] const std::size_t i1010,
-            [[maybe_unused]] const std::size_t i1011, const std::size_t i1100,
-            [[maybe_unused]] const std::size_t i1101,
-            [[maybe_unused]] const std::size_t i1110,
-            [[maybe_unused]] const std::size_t i1111) {
+        KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
+                      const std::size_t i0000, const std::size_t i0001,
+                      const std::size_t i0010, const std::size_t i0011,
+                      const std::size_t i0100, const std::size_t i0101,
+                      const std::size_t i0110, const std::size_t i0111,
+                      const std::size_t i1000, const std::size_t i1001,
+                      const std::size_t i1010, const std::size_t i1011,
+                      const std::size_t i1100, const std::size_t i1101,
+                      const std::size_t i1110, const std::size_t i1111) {
+            [[maybe_unused]] const auto i0000_ = i0000;
+            [[maybe_unused]] const auto i0001_ = i0001;
+            [[maybe_unused]] const auto i0010_ = i0010;
+            [[maybe_unused]] const auto i0100_ = i0100;
+            [[maybe_unused]] const auto i0101_ = i0101;
+            [[maybe_unused]] const auto i0110_ = i0110;
+            [[maybe_unused]] const auto i0111_ = i0111;
+            [[maybe_unused]] const auto i1000_ = i1000;
+            [[maybe_unused]] const auto i1001_ = i1001;
+            [[maybe_unused]] const auto i1010_ = i1010;
+            [[maybe_unused]] const auto i1011_ = i1011;
+            [[maybe_unused]] const auto i1101_ = i1101;
+            [[maybe_unused]] const auto i1110_ = i1110;
+            [[maybe_unused]] const auto i1111_ = i1111;
             arr(i0011) *= Kokkos::complex<PrecisionT>{0.0, 1.0};
             arr(i1100) *= Kokkos::complex<PrecisionT>{0.0, -1.0};
             kokkos_swap(arr(i1100), arr(i0011));
@@ -319,22 +333,29 @@ void applyGenDoubleExcitationPlus(
     [[maybe_unused]] const std::vector<PrecisionT> &params = {}) {
     applyNC4Functor(
         ExecutionSpace{}, arr_, num_qubits, wires,
-        KOKKOS_LAMBDA(
-            Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
-            [[maybe_unused]] const std::size_t i0000,
-            [[maybe_unused]] const std::size_t i0001,
-            [[maybe_unused]] const std::size_t i0010, const std::size_t i0011,
-            [[maybe_unused]] const std::size_t i0100,
-            [[maybe_unused]] const std::size_t i0101,
-            [[maybe_unused]] const std::size_t i0110,
-            [[maybe_unused]] const std::size_t i0111,
-            [[maybe_unused]] const std::size_t i1000,
-            [[maybe_unused]] const std::size_t i1001,
-            [[maybe_unused]] const std::size_t i1010,
-            [[maybe_unused]] const std::size_t i1011, const std::size_t i1100,
-            [[maybe_unused]] const std::size_t i1101,
-            [[maybe_unused]] const std::size_t i1110,
-            [[maybe_unused]] const std::size_t i1111) {
+        KOKKOS_LAMBDA(Kokkos::View<Kokkos::complex<PrecisionT> *> arr,
+                      const std::size_t i0000, const std::size_t i0001,
+                      const std::size_t i0010, const std::size_t i0011,
+                      const std::size_t i0100, const std::size_t i0101,
+                      const std::size_t i0110, const std::size_t i0111,
+                      const std::size_t i1000, const std::size_t i1001,
+                      const std::size_t i1010, const std::size_t i1011,
+                      const std::size_t i1100, const std::size_t i1101,
+                      const std::size_t i1110, const std::size_t i1111) {
+            [[maybe_unused]] const auto i0000_ = i0000;
+            [[maybe_unused]] const auto i0001_ = i0001;
+            [[maybe_unused]] const auto i0010_ = i0010;
+            [[maybe_unused]] const auto i0100_ = i0100;
+            [[maybe_unused]] const auto i0101_ = i0101;
+            [[maybe_unused]] const auto i0110_ = i0110;
+            [[maybe_unused]] const auto i0111_ = i0111;
+            [[maybe_unused]] const auto i1000_ = i1000;
+            [[maybe_unused]] const auto i1001_ = i1001;
+            [[maybe_unused]] const auto i1010_ = i1010;
+            [[maybe_unused]] const auto i1011_ = i1011;
+            [[maybe_unused]] const auto i1101_ = i1101;
+            [[maybe_unused]] const auto i1110_ = i1110;
+            [[maybe_unused]] const auto i1111_ = i1111;
             arr(i0011) *= Kokkos::complex<PrecisionT>{0.0, -1.0};
             arr(i1100) *= Kokkos::complex<PrecisionT>{0.0, 1.0};
             kokkos_swap(arr(i1100), arr(i0011));

From 76acd34662f485153189856aa761234c139592f2 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Fri, 21 Jun 2024 14:42:30 -0400
Subject: [PATCH 14/16] Update changelog

---
 .github/CHANGELOG.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/.github/CHANGELOG.md b/.github/CHANGELOG.md
index 4e7b73b709..84d4c75b4d 100644
--- a/.github/CHANGELOG.md
+++ b/.github/CHANGELOG.md
@@ -35,7 +35,6 @@
 
 ### Improvements
 
-
 * Release candidate branches are automatically switched over to using the new large GitHub runner pool.
   [(#769)](https://github.com/PennyLaneAI/pennylane-lightning/pull/769)
 
@@ -99,6 +98,9 @@
 
 ### Bug fixes
 
+* Fix regex matching issue with auto on-boarding of release candidate branch to using the large runner queue
+  [(#774)](https://github.com/PennyLaneAI/pennylane-lightning/pull/774)
+
 * Fix random CI failures for `lightning.tensor` python unit tests and ignore `lightning_tensor` paths.
   [(#761)](https://github.com/PennyLaneAI/pennylane-lightning/pull/761)
 

From 555ffa9d69e2b34ecb6697a985a1091e0e082b88 Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Fri, 21 Jun 2024 14:43:45 -0400
Subject: [PATCH 15/16] Address PR comments

---
 .github/workflows/determine-workflow-runner.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/determine-workflow-runner.yml b/.github/workflows/determine-workflow-runner.yml
index bd2d0b4afc..981c45f7d9 100644
--- a/.github/workflows/determine-workflow-runner.yml
+++ b/.github/workflows/determine-workflow-runner.yml
@@ -41,7 +41,7 @@ jobs:
           RC_BRANCH_FORMAT_REGEX: v[0-9]+\.[0-9]+\.[0-9]+-rc[0-9]?
           REPO_FULL_NAME: PennyLaneAI/pennylane-lightning
         run: |
-          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && "${{ github.event.pull_request.head.ref }}" =~ $RC_BRANCH_FORMAT_REGEX) ]]; then
+          if [[ '${{ contains(github.event.pull_request.labels.*.name, 'urgent') }}' == 'true' || ('${{ github.event.pull_request.head.repo.full_name }}' == "$REPO_FULL_NAME" && '${{ github.event.pull_request.head.ref }}' =~ $RC_BRANCH_FORMAT_REGEX) ]]; then
             echo "This job requires usage of the large runner group '$LARGE_RUNNER_GROUP_NAME'";
             echo "runner_group=$LARGE_RUNNER_GROUP_NAME" >> $GITHUB_OUTPUT
           else

From 0efacfef4a3a3f3d19dcb3166c7de92f6b8d440a Mon Sep 17 00:00:00 2001
From: Rashid N H M <95639609+rashidnhm@users.noreply.github.com>
Date: Fri, 21 Jun 2024 15:43:26 -0400
Subject: [PATCH 16/16] Update .github/CHANGELOG.md

Co-authored-by: Ali Asadi <10773383+maliasadi@users.noreply.github.com>
---
 .github/CHANGELOG.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/CHANGELOG.md b/.github/CHANGELOG.md
index 84d4c75b4d..e694d46ee1 100644
--- a/.github/CHANGELOG.md
+++ b/.github/CHANGELOG.md
@@ -98,7 +98,7 @@
 
 ### Bug fixes
 
-* Fix regex matching issue with auto on-boarding of release candidate branch to using the large runner queue
+* Fix regex matching issue with auto on-boarding of release candidate branch to using the large runner queue.
   [(#774)](https://github.com/PennyLaneAI/pennylane-lightning/pull/774)
 
 * Fix random CI failures for `lightning.tensor` python unit tests and ignore `lightning_tensor` paths.