diff --git a/docs/source/_templates/custom-module-template.rst b/docs/source/_templates/custom-module-template.rst
index 86174798..508b70b1 100644
--- a/docs/source/_templates/custom-module-template.rst
+++ b/docs/source/_templates/custom-module-template.rst
@@ -53,14 +53,14 @@
    {% endblock %}
 
 {% block modules %}
-{% if modules %}
+{% if all_modules %}
 .. rubric:: Modules
 
 .. autosummary::
    :toctree:
    :template: custom-module-template.rst
    :recursive:
-{% for item in modules %}
+{% for item in all_modules %}
    {{ item }}
 {%- endfor %}
 {% endif %}
diff --git a/docs/source/conf.py b/docs/source/conf.py
index f6ce9562..ab45288e 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -176,3 +176,7 @@ def setup(app: Sphinx):
 intersphinx_mapping = {
     "sklearn": ("https://scikit-learn.org/stable/", None),
 }
+
+suppress_warnings = [
+    'autosummary.import_cycle',
+]
diff --git a/pytorch_forecasting/metrics/_mqf2_utils.py b/pytorch_forecasting/metrics/_mqf2_utils.py
index 927ee56b..d5080ee2 100644
--- a/pytorch_forecasting/metrics/_mqf2_utils.py
+++ b/pytorch_forecasting/metrics/_mqf2_utils.py
@@ -12,12 +12,13 @@ class DeepConvexNet(DeepConvexFlow):
     r"""
     Class that takes a partially input convex neural network (picnn)
     as input and equips it with functions of logdet
-    computation (both estimation and exact computation)
+    computation (both estimation and exact computation).
     This class is based on DeepConvexFlow of the CP-Flow
     repo (https://github.com/CW-Huang/CP-Flow)
     For details of the logdet estimator, see
     ``Convex potential flows: Universal probability distributions
     with optimal transport and convex optimization``
+
     Parameters
     ----------
     picnn
@@ -94,6 +95,7 @@ class SequentialNet(SequentialFlow):
     layers and provides energy score computation
     This class is based on SequentialFlow of the CP-Flow repo
     (https://github.com/CW-Huang/CP-Flow)
+
     Parameters
     ----------
     networks
@@ -116,6 +118,7 @@ def es_sample(self, hidden_state: torch.Tensor, dimension: int) -> torch.Tensor:
         """
         Auxiliary function for energy score computation
         Drawing samples conditioned on the hidden state
+    
         Parameters
         ----------
         hidden_state
@@ -159,6 +162,7 @@ def energy_score(
         h_i is the hidden state associated with z_i,
         and es_num_samples is the number of samples drawn
         for each of w, w', w'' in energy score approximation
+
         Parameters
         ----------
         z
@@ -224,6 +228,7 @@ class MQF2Distribution(Distribution):
     Distribution class for the model MQF2 proposed in the paper
     ``Multivariate Quantile Function Forecaster``
     by Kan, Aubet, Januschowski, Park, Benidis, Ruthotto, Gasthaus
+
     Parameters
     ----------
     picnn
@@ -290,6 +295,7 @@ def stack_sliding_view(self, z: torch.Tensor) -> torch.Tensor:
         over the observations z
         Then, reshapes the observations into a 2-dimensional tensor for
         further computation
+
         Parameters
         ----------
         z
@@ -317,6 +323,7 @@ def log_prob(self, z: torch.Tensor) -> torch.Tensor:
         """
         Computes the log likelihood  log(g(z)) + logdet(dg(z)/dz),
         where g is the gradient of the picnn
+
         Parameters
         ----------
         z
@@ -346,6 +353,7 @@ def energy_score(self, z: torch.Tensor) -> torch.Tensor:
         h_i is the hidden state associated with z_i,
         and es_num_samples is the number of samples drawn
         for each of w, w', w'' in energy score approximation
+
         Parameters
         ----------
         z
@@ -370,6 +378,7 @@ def energy_score(self, z: torch.Tensor) -> torch.Tensor:
     def rsample(self, sample_shape: torch.Size = torch.Size()) -> torch.Tensor:
         """
         Generates the sample paths
+
         Parameters
         ----------
         sample_shape
@@ -377,7 +386,7 @@ def rsample(self, sample_shape: torch.Size = torch.Size()) -> torch.Tensor:
         Returns
         -------
         sample_paths
-            Tesnor of shape (batch_size, *sample_shape, prediction_length)
+            Tesnor of shape (batch_size, * sample_shape, prediction_length)
         """
 
         numel_batch = self.numel_batch
@@ -407,6 +416,7 @@ def rsample(self, sample_shape: torch.Size = torch.Size()) -> torch.Tensor:
     def quantile(self, alpha: torch.Tensor, hidden_state: Optional[torch.Tensor] = None) -> torch.Tensor:
         """
         Generates the predicted paths associated with the quantile levels alpha
+
         Parameters
         ----------
         alpha