diff --git a/.github/workflows/ci_cpu.yml b/.github/workflows/ci_cpu.yml
new file mode 100644
index 00000000..bc2aedc3
--- /dev/null
+++ b/.github/workflows/ci_cpu.yml
@@ -0,0 +1,170 @@
+name: CI_CPU
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  schedule:
+    - cron: '4 4 * * *'  # This schedule runs the nightly job every night at 4:04AM
+
+
+jobs:
+  ########### LINT ##############
+  lint_py39_torch_release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 black isort
+          ./scripts/install_via_pip.sh
+      - name: Lint with flake8
+        run: flake8 --config ./.github/workflows/flake8_config.ini
+      - name: Lint with black
+        run: black --check --diff --color .
+      - name: Check import order with isort
+        run: isort -v -l 88 -o opacus --lines-after-imports 2 -m 3 --trailing-comma --check-only .
+
+  ########### UNIT TESTS ##############
+  unittest_py38_torch_release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest coverage coveralls
+          ./scripts/install_via_pip.sh
+      - name: Run unit tests
+        run: |
+          mkdir unittest-py38-release-reports
+          coverage run -m pytest --doctest-modules -p conftest --junitxml=unittest-py38-release-reports/junit.xml opacus
+          coverage report -i -m
+      - name: Store test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: unittest-py38-release-reports
+          path: unittest-py38-release-reports
+
+  unittest_py39_torch_release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest coverage coveralls
+          ./scripts/install_via_pip.sh
+      - name: Run unit tests
+        run: |
+          mkdir unittest-py39-release-reports
+          coverage run -m pytest --doctest-modules -p conftest --junitxml=unittest-py39-release-reports/junit.xml opacus
+          coverage report -i -m
+      - name: Store test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: unittest-py39-release-reports
+          path: unittest-py39-release-reports
+
+  prv_accountant_values:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          ./scripts/install_via_pip.sh
+      - name: Run prv accountant unit tests
+        run: |
+          python -m unittest opacus.tests.prv_accountant
+
+  ########### NIGHTLY TEST ##############
+  unittest_py39_torch_nightly:
+    runs-on: ubuntu-latest
+    if: ${{ github.event_name == 'schedule' }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest coverage coveralls
+          ./scripts/install_via_pip.sh -n
+      - name: Run unit tests
+        run: |
+          mkdir unittest-py39-nightly-reports
+          python -m pytest --doctest-modules -p conftest --junitxml=unittest-py39-nightly-reports/junit.xml opacus
+      - name: Store test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: unittest-py39-nightly-reports
+          path: unittest-py39-nightly-reports
+
+  ########### INTEGRATION TEST ##############
+  integrationtest_py39_torch_release_cpu:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest coverage coveralls
+          ./scripts/install_via_pip.sh
+      - name: Run MNIST integration test (CPU)
+        run: |
+          mkdir -p runs/mnist/data
+          mkdir -p runs/mnist/test-reports
+          coverage run examples/mnist.py --lr 0.25 --sigma 0.7 -c 1.5 --batch-size 64 --epochs 1 --data-root runs/mnist/data --n-runs 1 --device cpu
+          python -c "import torch; accuracy = torch.load('run_results_mnist_0.25_0.7_1.5_64_1.pt'); exit(0) if (accuracy[0]>0.78 and accuracy[0]<0.95) else exit(1)"
+          coverage report -i -m
+      - name: Store test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: mnist-cpu-reports
+          path: runs/mnist/test-reports
+
+  ######## FINISH COVERALLS ##########
+  finish_coveralls_parallel:
+    needs: [unittest_py38_torch_release, unittest_py39_torch_release, integrationtest_py39_torch_release_cpu]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Finish Coveralls Parallel
+        uses: coverallsapp/github-action@v2
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          parallel-finished: true
diff --git a/.github/workflows/ci_gpu.yml b/.github/workflows/ci_gpu.yml
new file mode 100644
index 00000000..90dca200
--- /dev/null
+++ b/.github/workflows/ci_gpu.yml
@@ -0,0 +1,173 @@
+name: CI_GPU
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+  unittest_multi_gpu:
+    runs-on: linux.4xlarge.nvidia.gpu
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          ./scripts/install_via_pip.sh -c
+
+      - name: Run multi-GPU unit tests
+        run: |
+          nvidia-smi
+          nvcc --version
+          python -m unittest opacus.tests.multigpu_gradcheck.GradientComputationTest.test_gradient_correct
+
+
+  integrationtest_py39_torch_release_cuda:
+    runs-on: ubuntu-latest
+    container:
+      # https://hub.docker.com/r/nvidia/cuda
+      image: nvidia/cuda:12.3.1-base-ubuntu22.04
+      options: --gpus all
+    env:
+      TZ: 'UTC'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest coverage coveralls
+          ./scripts/install_via_pip.sh -c
+
+      - name: Install CUDA toolkit and cuDNN
+        run: |
+          apt-get update
+          apt-get install -y --no-install-recommends \
+            cuda-toolkit-11-1 \
+            libcudnn8=8.1.1.33-1+cuda11.1 \
+            libcudnn8-dev=8.1.1.33-1+cuda11.1
+
+      - name: Run MNIST integration test (CUDA)
+        run: |
+          mkdir -p runs/mnist/data
+          mkdir -p runs/mnist/test-reports
+          python examples/mnist.py --lr 0.25 --sigma 0.7 -c 1.5 --batch-size 64 --epochs 1 --data-root runs/mnist/data --n-runs 1 --device cuda
+          python -c "import torch; accuracy = torch.load('run_results_mnist_0.25_0.7_1.5_64_1.pt'); exit(0) if (accuracy[0]>0.78 and accuracy[0]<0.95) else exit(1)"
+
+      - name: Store MNIST test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: mnist-gpu-reports
+          path: runs/mnist/test-reports
+
+      - name: Run CIFAR10 integration test (CUDA)
+        run: |
+          mkdir -p runs/cifar10/data
+          mkdir -p runs/cifar10/logs
+          mkdir -p runs/cifar10/test-reports
+          pip install tensorboard
+          python examples/cifar10.py --lr 0.1 --sigma 1.5 -c 10 --batch-size 2000 --epochs 10 --data-root runs/cifar10/data --log-dir runs/cifar10/logs --device cuda
+          python -c "import torch; model = torch.load('model_best.pth.tar'); exit(0) if (model['best_acc1']>0.4 and model['best_acc1']<0.49) else exit(1)"
+          python examples/cifar10.py --lr 0.1 --sigma 1.5 -c 10 --batch-size 2000 --epochs 10 --data-root runs/cifar10/data --log-dir runs/cifar10/logs --device cuda --grad_sample_mode no_op
+          python -c "import torch; model = torch.load('model_best.pth.tar'); exit(0) if (model['best_acc1']>0.4 and model['best_acc1']<0.49) else exit(1)"
+
+      - name: Store CIFAR10 test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: cifar10-gpu-reports
+          path: runs/cifar10/test-reports
+
+      - name: Run IMDb integration test (CUDA)
+        run: |
+          mkdir -p runs/imdb/data
+          mkdir -p runs/imdb/test-reports
+          pip install --user datasets transformers
+          python examples/imdb.py --lr 0.02 --sigma 1.0 -c 1.0 --batch-size 64 --max-sequence-length 256 --epochs 2 --data-root runs/imdb/data --device cuda
+          python -c "import torch; accuracy = torch.load('run_results_imdb_classification.pt'); exit(0) if (accuracy>0.54 and accuracy<0.66) else exit(1)"
+
+      - name: Store IMDb test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: imdb-gpu-reports
+          path: runs/imdb/test-reports
+
+      - name: Run charlstm integration test (CUDA)
+        run: |
+          mkdir -p runs/charlstm/data
+          wget https://download.pytorch.org/tutorial/data.zip -O runs/charlstm/data/data.zip
+          unzip runs/charlstm/data/data.zip -d runs/charlstm/data
+          rm runs/charlstm/data/data.zip
+          mkdir -p runs/charlstm/test-reports
+          pip install scikit-learn
+          python examples/char-lstm-classification.py --epochs=20 --learning-rate=2.0 --hidden-size=128 --delta=8e-5 --batch-size 400 --n-layers=1 --sigma=1.0 --max-per-sample-grad-norm=1.5 --data-root="runs/charlstm/data/data/names/" --device cuda --test-every 5
+          python -c "import torch; accuracy = torch.load('run_results_chr_lstm_classification.pt'); exit(0) if (accuracy>0.60 and accuracy<0.80) else exit(1)"
+
+      - name: Store test results
+        uses: actions/upload-artifact@v2
+        with:
+          name: charlstm-gpu-reports
+          path: runs/charlstm/test-reports
+
+  micro_benchmarks_py39_torch_release_cuda:
+    runs-on: ubuntu-latest
+    needs: [integrationtest_py39_torch_release_cuda]
+    container:
+      # https://hub.docker.com/r/nvidia/cuda
+      image: nvidia/cuda:12.3.1-base-ubuntu22.04
+      options: --gpus all
+    env:
+      TZ: 'UTC'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest coverage coveralls
+          ./scripts/install_via_pip.sh
+
+      - name: Install CUDA toolkit and cuDNN
+        run: |
+          apt-get update
+          apt-get install -y --no-install-recommends \
+            cuda-toolkit-11-1 \
+            libcudnn8=8.1.1.33-1+cuda11.1 \
+            libcudnn8-dev=8.1.1.33-1+cuda11.1
+
+      - name: Run benchmark integration tests (CUDA)
+        run: |
+          mkdir -p benchmarks/results/raw
+          python benchmarks/run_benchmarks.py --batch_size 16 --layers "groupnorm instancenorm layernorm" --config_file ./benchmarks/config.json --root ./benchmarks/results/raw/ --cont
+          IFS=$' ';layers=("groupnorm" "instancenorm" "layernorm"); rm -rf /tmp/report_layers; mkdir -p /tmp/report_layers; IFS=$'\n'; files=`( echo "${layers[*]}" ) | sed 's/.*/.\/benchmarks\/results\/raw\/&*/'`
+          cp -v ${files[@]} /tmp/report_layers
+          report_id=`IFS=$'-'; echo "${layers[*]}"`
+          python benchmarks/generate_report.py --path-to-results /tmp/report_layers --save-path benchmarks/results/report-${report_id}.csv --format csv
+          python benchmarks/generate_report.py --path-to-results /tmp/report_layers --save-path benchmarks/results/report-${report_id}.pkl --format pkl
+          python benchmarks/check_threshold.py --report-path "./benchmarks/results/report-"$report_id".pkl" --metric runtime --threshold 3.0 --column "hooks/baseline"
+          python benchmarks/check_threshold.py --report-path "./benchmarks/results/report-"$report_id".pkl" --metric memory --threshold 1.6 --column "hooks/baseline"
+
+      - name: Store artifacts
+        uses: actions/upload-artifact@v2
+        with:
+          name: benchmarks-reports
+          path: benchmarks/results/
diff --git a/.github/workflows/flake8_config.ini b/.github/workflows/flake8_config.ini
new file mode 100644
index 00000000..988ed7f3
--- /dev/null
+++ b/.github/workflows/flake8_config.ini
@@ -0,0 +1,119 @@
+[flake8]
+select = B,C,E,F,P,W,B9
+max-line-length = 80
+# Main Explanation Docs: https://github.com/grantmcconnaughey/Flake8Rules
+ignore =
+  # Black conflicts and overlaps.
+  # Found in https://github.com/psf/black/issues/429
+  # B950: Line too long. (Use `arc lint`'s LINEWRAP instead)
+  B950,
+  # E111: Indentation is not a multiple of four.
+  E111,
+  # E115: Expected an indented block (comment).
+  E115,
+  # E117: Over-indented.
+  E117,
+  # E121: Continuation line under-indented for hanging indent.
+  E121,
+  # E122: Continuation line missing indentation or outdented.
+  E122,
+  # E123: Closing bracket does not match indentation of opening bracket's line.
+  E123,
+  # E124: Closing bracket does not match visual indentation.
+  E124,
+  # E125: Continuation line with same indent as next logical line.
+  E125,
+  # E126: Continuation line over-indented for hanging indent.
+  E126,
+  # E127: Continuation line over-indented for visual indent.
+  E127,
+  # E128: Continuation line under-indented for visual indent.
+  E128,
+  # E129: Visually indented line with same indent as next logical line.
+  E129,
+  # E201: Whitespace after '('.
+  E201,
+  # E202: Whitespace before ')'.
+  E202,
+  # E203: Whitespace before ':'.
+  E203,
+  # E221: Multiple spaces before operator.
+  E221,
+  # E222: Multiple spaces after operator.
+  E222,
+  # E225: Missing whitespace around operator.
+  E225,
+  # E226: Missing whitespace around arithmetic operator.
+  E226,
+  # E227: Missing whitespace around bitwise or shift operator.
+  E227,
+  # E231: Missing whitespace after ',', ';', or ':'.
+  E231,
+  # E241: Multiple spaces after ','.
+  E241,
+  # E251: Unexpected spaces around keyword / parameter equals.
+  E251,
+  # E261: At least two spaces before inline comment.
+  E261,
+  # E262: Inline comment should start with '# '.
+  E262,
+  # E265: Block comment should start with '# '.
+  E265,
+  # E271: Multiple spaces after keyword.
+  E271,
+  # E272: Multiple spaces before keyword.
+  E272,
+  # E301: Expected 1 blank line, found 0.
+  E301,
+  # E302: Expected 2 blank lines, found 0.
+  E302,
+  # E303: Too many blank lines (3).
+  E303,
+  # E305: Expected 2 blank lines after end of function or class.
+  E305,
+  # E306: Expected 1 blank line before a nested definition.
+  E306,
+  # E501: Line too long (82 > 79 characters).
+  E501,
+  # E502: The backslash is redundant between brackets.
+  E502,
+  # E701: Multiple statements on one line (colon).
+  E701,
+  # E702: Multiple statements on one line (semicolon).
+  E702,
+  # E703: Statement ends with a semicolon.
+  E703,
+  # E704: Multiple statements on one line (def).
+  E704,
+  # W291: Trailing whitespace.
+  W291,
+  # W292: No newline at end of file.
+  W292,
+  # W293: Blank line contains whitespace.
+  W293,
+  # W391: Blank line at end of file.
+  W391,
+
+  # Too opinionated.
+  # E265: Block comment should start with '# '.
+  E265,
+  # E266: Too many leading '#' for block comment.
+  E266,
+  # E402: Module level import not at top of file.
+  E402,
+  # E722: Do not use bare except, specify exception instead. (Duplicate of B001)
+  E722,
+  # F811: Redefinition of unused name from line n.
+  F811,
+  # P207: (Duplicate of B003)
+  P207,
+  # P208: (Duplicate of C403)
+  P208,
+  # W503: Line break occurred before a binary operator.
+  W503
+
+exclude =
+  .hg,
+  __pycache__,
+
+max-complexity = 12
diff --git a/examples/dcgan.py b/examples/dcgan.py
index c1065f12..585e145a 100644
--- a/examples/dcgan.py
+++ b/examples/dcgan.py
@@ -201,7 +201,7 @@ def __init__(self, ngpu):
             nn.ReLU(True),
             # state size. (ngf) x 32 x 32
             nn.ConvTranspose2d(ngf, nc, 4, 2, 1, bias=False),
-            nn.Tanh()
+            nn.Tanh(),
             # state size. (nc) x 64 x 64
         )
 
diff --git a/opacus/accountants/analysis/prv/domain.py b/opacus/accountants/analysis/prv/domain.py
index 5e86502d..220dbbd9 100644
--- a/opacus/accountants/analysis/prv/domain.py
+++ b/opacus/accountants/analysis/prv/domain.py
@@ -12,6 +12,7 @@ class Domain:
     Stores relevant information about the domain on which PRVs are discretized, and
     includes a few convenience methods for manipulating it.
     """
+
     t_min: float
     t_max: float
     size: int
diff --git a/opacus/layers/dp_rnn.py b/opacus/layers/dp_rnn.py
index 5f5c6819..405ec70b 100644
--- a/opacus/layers/dp_rnn.py
+++ b/opacus/layers/dp_rnn.py
@@ -405,9 +405,12 @@ def forward(
             for direction, (cell, h0, c0) in directions:
                 # apply single direction layer (with dropout)
                 out_layer, h, c = self.forward_layer(
-                    x
-                    if layer == 0
-                    else output,  # [T, B, D/H/2H] / tuple T x [B, D/H/2H]
+                    (
+                        x
+                        if layer == 0
+                        else output
+                        # [T, B, D/H/2H] / tuple T x [B, D/H/2H]
+                    ),
                     h0,  # [B, H]
                     c0,
                     batch_sizes,
diff --git a/opacus/privacy_engine.py b/opacus/privacy_engine.py
index 0ca6811b..555769d0 100644
--- a/opacus/privacy_engine.py
+++ b/opacus/privacy_engine.py
@@ -536,9 +536,9 @@ def save_checkpoint(
         if noise_scheduler is not None:
             checkpoint_dict["noise_scheduler_state_dict"] = noise_scheduler.state_dict()
         if grad_clip_scheduler is not None:
-            checkpoint_dict[
-                "grad_clip_scheduler_state_dict"
-            ] = grad_clip_scheduler.state_dict()
+            checkpoint_dict["grad_clip_scheduler_state_dict"] = (
+                grad_clip_scheduler.state_dict()
+            )
 
         torch.save(checkpoint_dict, path, **(torch_save_kwargs or {}))
 
diff --git a/opacus/tests/grad_samples/conv2d_test.py b/opacus/tests/grad_samples/conv2d_test.py
index b0deae3f..d1178506 100644
--- a/opacus/tests/grad_samples/conv2d_test.py
+++ b/opacus/tests/grad_samples/conv2d_test.py
@@ -90,9 +90,9 @@ def test_conv2d(
             # Test 'convolution as a backward' GSM
             # 'convolution as a backward' doesn't support padding=same
             conv2d_gsm = GradSampleModule.GRAD_SAMPLERS[nn.Conv2d]
-            GradSampleModule.GRAD_SAMPLERS[
-                nn.Conv2d
-            ] = convolution2d_backward_as_a_convolution
+            GradSampleModule.GRAD_SAMPLERS[nn.Conv2d] = (
+                convolution2d_backward_as_a_convolution
+            )
             self.run_test(
                 x,
                 conv,
diff --git a/opacus/tests/privacy_engine_test.py b/opacus/tests/privacy_engine_test.py
index 022acfa3..f2ed1a32 100644
--- a/opacus/tests/privacy_engine_test.py
+++ b/opacus/tests/privacy_engine_test.py
@@ -87,9 +87,11 @@ def _init_vanilla_training(
     ):
         model = self._init_model()
         optimizer = torch.optim.SGD(
-            model.parameters()
-            if not opt_exclude_frozen
-            else [p for p in model.parameters() if p.requires_grad],
+            (
+                model.parameters()
+                if not opt_exclude_frozen
+                else [p for p in model.parameters() if p.requires_grad]
+            ),
             lr=self.LR,
             momentum=0,
         )
@@ -112,9 +114,11 @@ def _init_private_training(
         model = self._init_model()
         model = PrivacyEngine.get_compatible_module(model)
         optimizer = torch.optim.SGD(
-            model.parameters()
-            if not opt_exclude_frozen
-            else [p for p in model.parameters() if p.requires_grad],
+            (
+                model.parameters()
+                if not opt_exclude_frozen
+                else [p for p in model.parameters() if p.requires_grad]
+            ),
             lr=self.LR,
             momentum=0,
         )