Add minor updates

src/deepsparse/benchmark/stream_benchmark.py

@@ -131,8 +131,8 @@ def model_stream_benchmark(
     # given amount of wallclock time. This calculation as-is includes the test overhead
     # such as saving timing results for each iteration so it isn't a best-case but is a
     # realistic case.
-    first_start_time = min([b[0] for b in batch_times])
-    last_end_time = max([b[1] for b in batch_times])
+    first_start_time = min(b[0] for b in batch_times)
+    last_end_time = max(b[1] for b in batch_times)
     total_time_executing = last_end_time - first_start_time
 
     items_per_sec = (model.batch_size * len(batch_times)) / total_time_executing

src/deepsparse/pipeline.py

@@ -282,10 +282,7 @@ def __call__(self, *args, **kwargs) -> BaseModel:
             # ------ POSTPROCESSING ------
             timer.start(InferenceStages.POST_PROCESS)
             pipeline_outputs = self.process_engine_outputs(engine_outputs, **context)
-            if not (
-                isinstance(pipeline_outputs, (self.output_schema, Generator))
-                or isinstance(pipeline_outputs, Generator)
-            ):
+            if not isinstance(pipeline_outputs, (self.output_schema, Generator)):
                 raise ValueError(
                     f"Outputs of {self.__class__} must be instances of "
                     f"{self.output_schema} found output of type "

src/deepsparse/transformers/metrics.py

@@ -96,7 +96,7 @@ def add_batch(self, predictions: List[str]):
                 list(compress(sequence, attn_mask))
                 for (sequence, attn_mask) in zip(encoded_batch, attention_mask)
             ]
-            max_sequence_len = max([len(sequence) for sequence in encoded_batch])
+            max_sequence_len = max(len(sequence) for sequence in encoded_batch)
 
             encoded_batch = [
                 pad_to_fixed_length(numpy.array(sequence), max_sequence_len)

src/deepsparse/transformers/pipelines/text_generation.py

@@ -928,7 +928,7 @@ def join_engine_outputs(
                 # different lengths
 
                 # find the longest sequence in the batch of tokens
-                max_len = max([token.shape[1] for token in tokens])
+                max_len = max(token.shape[1] for token in tokens)
 
                 # pad all tokens to the same length
                 tokens = [
@@ -942,7 +942,7 @@ def join_engine_outputs(
                 ]
 
                 # find the longest sequence in the batch of logits
-                max_len = max([logits.shape[1] for logits in logits])
+                max_len = max(logits.shape[1] for logits in logits)
 
                 # pad all logits to the same length
                 logits = [