diff --git a/benchmarks/compare-fastrnn-results.py b/benchmarks/compare-fastrnn-results.py
index 64c8d8dd98d..35d907d0820 100644
--- a/benchmarks/compare-fastrnn-results.py
+++ b/benchmarks/compare-fastrnn-results.py
@@ -2,6 +2,7 @@ import argparse
 import json
 from collections import namedtuple
 
+
 Result = namedtuple("Result", ["name", "base_time", "diff_time"])
 
 
diff --git a/benchmarks/distributed/rpc/parameter_server/data/__init__.py b/benchmarks/distributed/rpc/parameter_server/data/__init__.py
index cf96abd4c68..3b37129e9a5 100644
--- a/benchmarks/distributed/rpc/parameter_server/data/__init__.py
+++ b/benchmarks/distributed/rpc/parameter_server/data/__init__.py
@@ -1,3 +1,4 @@
 from .DummyData import DummyData
 
+
 data_map = {"DummyData": DummyData}
diff --git a/benchmarks/distributed/rpc/parameter_server/models/__init__.py b/benchmarks/distributed/rpc/parameter_server/models/__init__.py
index cfeeaaf4c77..0b53de4dd1b 100644
--- a/benchmarks/distributed/rpc/parameter_server/models/__init__.py
+++ b/benchmarks/distributed/rpc/parameter_server/models/__init__.py
@@ -1,3 +1,4 @@
 from .DummyModel import DummyModel
 
+
 model_map = {"DummyModel": DummyModel}
diff --git a/benchmarks/distributed/rpc/parameter_server/server/__init__.py b/benchmarks/distributed/rpc/parameter_server/server/__init__.py
index 54d8983ea9f..d204b3d03c2 100644
--- a/benchmarks/distributed/rpc/parameter_server/server/__init__.py
+++ b/benchmarks/distributed/rpc/parameter_server/server/__init__.py
@@ -1,5 +1,6 @@
 from .server import AverageBatchParameterServer, AverageParameterServer
 
+
 server_map = {
     "AverageParameterServer": AverageParameterServer,
     "AverageBatchParameterServer": AverageBatchParameterServer,
diff --git a/benchmarks/distributed/rpc/parameter_server/trainer/__init__.py b/benchmarks/distributed/rpc/parameter_server/trainer/__init__.py
index c1f51adec32..12d6f9e7f05 100644
--- a/benchmarks/distributed/rpc/parameter_server/trainer/__init__.py
+++ b/benchmarks/distributed/rpc/parameter_server/trainer/__init__.py
@@ -6,6 +6,7 @@ from .iteration_steps import basic_iteration_step
 from .preprocess_data import preprocess_dummy_data
 from .trainer import DdpTrainer
 
+
 criterion_map = {"cel": cel}
 
 ddp_hook_map = {
diff --git a/benchmarks/distributed/rpc/parameter_server/utils.py b/benchmarks/distributed/rpc/parameter_server/utils.py
index efa470bd44c..baa4a9a9e9e 100644
--- a/benchmarks/distributed/rpc/parameter_server/utils.py
+++ b/benchmarks/distributed/rpc/parameter_server/utils.py
@@ -1,5 +1,6 @@
 import torch
 
+
 RPC_SPARSE = "rpc_sparse"
 RPC_DENSE = "rpc_dense"
 
diff --git a/benchmarks/distributed/rpc/rl/coordinator.py b/benchmarks/distributed/rpc/rl/coordinator.py
index 75b1780a34f..8dff633d2e1 100644
--- a/benchmarks/distributed/rpc/rl/coordinator.py
+++ b/benchmarks/distributed/rpc/rl/coordinator.py
@@ -1,13 +1,13 @@
 import time
 
 import numpy as np
-
 from agent import AgentBase
 from observer import ObserverBase
 
 import torch
 import torch.distributed.rpc as rpc
 
+
 COORDINATOR_NAME = "coordinator"
 AGENT_NAME = "agent"
 OBSERVER_NAME = "observer{}"
diff --git a/benchmarks/distributed/rpc/rl/launcher.py b/benchmarks/distributed/rpc/rl/launcher.py
index 22ae8962975..7c6f74524d7 100644
--- a/benchmarks/distributed/rpc/rl/launcher.py
+++ b/benchmarks/distributed/rpc/rl/launcher.py
@@ -1,5 +1,4 @@
 import argparse
-
 import json
 import os
 import time
@@ -9,6 +8,7 @@ from coordinator import CoordinatorBase
 import torch.distributed.rpc as rpc
 import torch.multiprocessing as mp
 
+
 COORDINATOR_NAME = "coordinator"
 AGENT_NAME = "agent"
 OBSERVER_NAME = "observer{}"
diff --git a/benchmarks/dynamo/benchmarks.py b/benchmarks/dynamo/benchmarks.py
index c209781ffd6..6ed845a9fcb 100755
--- a/benchmarks/dynamo/benchmarks.py
+++ b/benchmarks/dynamo/benchmarks.py
@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
+
 import argparse
 import os
 import sys
-
 from typing import Set
 
 
diff --git a/benchmarks/dynamo/ci_expected_accuracy/update_expected.py b/benchmarks/dynamo/ci_expected_accuracy/update_expected.py
index 1f3a02b69a5..29d204c02e2 100644
--- a/benchmarks/dynamo/ci_expected_accuracy/update_expected.py
+++ b/benchmarks/dynamo/ci_expected_accuracy/update_expected.py
@@ -30,6 +30,7 @@ from zipfile import ZipFile
 import pandas as pd
 import requests
 
+
 # Note: the public query url targets this rockset lambda:
 # https://console.rockset.com/lambdas/details/commons.artifacts
 ARTIFACTS_QUERY_URL = "https://api.usw2a1.rockset.com/v1/public/shared_lambdas/4ca0033e-0117-41f5-b043-59cde19eff35"
diff --git a/benchmarks/dynamo/combine_csv.py b/benchmarks/dynamo/combine_csv.py
index 560b8a3cf24..e4c2e0f0951 100644
--- a/benchmarks/dynamo/combine_csv.py
+++ b/benchmarks/dynamo/combine_csv.py
@@ -6,6 +6,7 @@ import csv
 import sys
 from collections import defaultdict
 
+
 assert len(sys.argv) == 3
 
 RESULTS = defaultdict(dict)
diff --git a/benchmarks/dynamo/common.py b/benchmarks/dynamo/common.py
index 76ca81fb2c5..8069ca11520 100644
--- a/benchmarks/dynamo/common.py
+++ b/benchmarks/dynamo/common.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 from __future__ import annotations
 
 import abc
diff --git a/benchmarks/dynamo/dist_util.py b/benchmarks/dynamo/dist_util.py
index 98cc274a4c6..c1036bbb1e4 100644
--- a/benchmarks/dynamo/dist_util.py
+++ b/benchmarks/dynamo/dist_util.py
@@ -15,6 +15,7 @@ from torch.distributed.algorithms._checkpoint.checkpoint_wrapper import (
 from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
 from torch.distributed.fsdp.wrap import ModuleWrapPolicy
 
+
 try:
     from .torchbench import setup_torchbench_cwd
 except ImportError:
diff --git a/benchmarks/dynamo/distributed.py b/benchmarks/dynamo/distributed.py
index 9d99c4fcb6e..d2af630c8bf 100644
--- a/benchmarks/dynamo/distributed.py
+++ b/benchmarks/dynamo/distributed.py
@@ -10,6 +10,7 @@ from torch._dynamo.testing import reduce_to_scalar_loss
 from torch.nn.parallel import DistributedDataParallel as DDP
 from torch.profiler import profile, ProfilerActivity, record_function
 
+
 try:
     from .common import timed
     from .dist_util import apply_fsdp, cleanup, get_model, model_iter_fn, setup
diff --git a/benchmarks/dynamo/huggingface.py b/benchmarks/dynamo/huggingface.py
index 46492cc2dfc..32708ccfbf9 100755
--- a/benchmarks/dynamo/huggingface.py
+++ b/benchmarks/dynamo/huggingface.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 import importlib
 import logging
 import os
@@ -7,16 +8,17 @@ import subprocess
 import sys
 import warnings
 
+
 try:
     from .common import BenchmarkRunner, download_retry_decorator, main, reset_rng_state
 except ImportError:
     from common import BenchmarkRunner, download_retry_decorator, main, reset_rng_state
 
 import torch
-
 from torch._dynamo.testing import collect_results
 from torch._dynamo.utils import clone_inputs
 
+
 log = logging.getLogger(__name__)
 
 # Enable FX graph caching
diff --git a/benchmarks/dynamo/microbenchmarks/bench_mm_fusion.py b/benchmarks/dynamo/microbenchmarks/bench_mm_fusion.py
index 424edac2b8f..b0e083b0007 100644
--- a/benchmarks/dynamo/microbenchmarks/bench_mm_fusion.py
+++ b/benchmarks/dynamo/microbenchmarks/bench_mm_fusion.py
@@ -1,12 +1,13 @@
 # flake8: noqa
+
 import triton
 from prettytable import PrettyTable
 
 import torch
-
 import torch._dynamo
 import torch._inductor.config
 
+
 # torch._inductor.config.debug = True
 torch._inductor.config.triton.dense_indexing = True
 torch.manual_seed(0)
diff --git a/benchmarks/dynamo/microbenchmarks/fx_microbenchmarks.py b/benchmarks/dynamo/microbenchmarks/fx_microbenchmarks.py
index 2c575c69418..0f957dc4aaf 100644
--- a/benchmarks/dynamo/microbenchmarks/fx_microbenchmarks.py
+++ b/benchmarks/dynamo/microbenchmarks/fx_microbenchmarks.py
@@ -2,6 +2,7 @@ import timeit
 
 import torch.fx
 
+
 N = 100000
 K = 1000
 
diff --git a/benchmarks/dynamo/microbenchmarks/inductor_bmm.py b/benchmarks/dynamo/microbenchmarks/inductor_bmm.py
index 5c5326beef6..3e97680a3ba 100644
--- a/benchmarks/dynamo/microbenchmarks/inductor_bmm.py
+++ b/benchmarks/dynamo/microbenchmarks/inductor_bmm.py
@@ -1,7 +1,6 @@
 from benchmark_helper import time_with_torch_timer
 
 import torch
-
 import torch._dynamo
 import torch._dynamo.config
 import torch._inductor.config as config
diff --git a/benchmarks/dynamo/microbenchmarks/inductor_mm.py b/benchmarks/dynamo/microbenchmarks/inductor_mm.py
index 2db6fc0e722..6d26c9d029e 100644
--- a/benchmarks/dynamo/microbenchmarks/inductor_mm.py
+++ b/benchmarks/dynamo/microbenchmarks/inductor_mm.py
@@ -2,11 +2,11 @@ import triton
 from benchmark_helper import time_with_torch_timer
 
 import torch
-
 import torch._dynamo
 import torch._dynamo.config
 import torch._inductor.config as config
 
+
 # The flag below controls whether to allow TF32 on matmul. This flag defaults to True.
 torch.backends.cuda.matmul.allow_tf32 = True
 # The flag below controls whether to allow TF32 on cuDNN. This flag defaults to True.
diff --git a/benchmarks/dynamo/microbenchmarks/matmul_relu.py b/benchmarks/dynamo/microbenchmarks/matmul_relu.py
index 9baf893af96..bc975b6455f 100644
--- a/benchmarks/dynamo/microbenchmarks/matmul_relu.py
+++ b/benchmarks/dynamo/microbenchmarks/matmul_relu.py
@@ -1,10 +1,10 @@
 from benchmark_helper import time_with_torch_timer
 
 import torch
-
 import torch._dynamo
 import torch._inductor.config as inductor_config
 
+
 inductor_config.triton.mm = "triton"
 
 
diff --git a/benchmarks/dynamo/microbenchmarks/microbench.py b/benchmarks/dynamo/microbenchmarks/microbench.py
index fa01824afcf..302f6857e77 100755
--- a/benchmarks/dynamo/microbenchmarks/microbench.py
+++ b/benchmarks/dynamo/microbenchmarks/microbench.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 import argparse
 import inspect
 import sys
@@ -7,13 +8,13 @@ import numpy as np
 import tabulate
 
 import torch
-
 import torch._inductor
 from torch._dynamo.backends.cudagraphs import cudagraphs_inner
 from torch._dynamo.testing import same
 from torch._inductor.compile_fx import compile_fx
 from torch._inductor.utils import timed
 
+
 aten = torch.ops.aten
 
 try:
diff --git a/benchmarks/dynamo/microbenchmarks/operator_inp_utils.py b/benchmarks/dynamo/microbenchmarks/operator_inp_utils.py
index 28139e93390..602c3bc516f 100644
--- a/benchmarks/dynamo/microbenchmarks/operator_inp_utils.py
+++ b/benchmarks/dynamo/microbenchmarks/operator_inp_utils.py
@@ -12,6 +12,7 @@ from torch.utils import _pytree as pytree
 from torch.utils._python_dispatch import TorchDispatchMode
 from torch.utils._pytree import tree_map
 
+
 log = logging.getLogger(__name__)
 
 OP_INP_DIRECTORY = os.path.join(os.path.dirname(__file__), "operator_inp_logs")
diff --git a/benchmarks/dynamo/microbenchmarks/operatorbench.py b/benchmarks/dynamo/microbenchmarks/operatorbench.py
index dcc2b428d2e..7965e4ff01d 100644
--- a/benchmarks/dynamo/microbenchmarks/operatorbench.py
+++ b/benchmarks/dynamo/microbenchmarks/operatorbench.py
@@ -1,10 +1,10 @@
 #!/usr/bin/env python3
+
 import click
 import numpy as np
 from operator_inp_utils import OperatorInputsLoader
 
 import torch
-
 from torch._dynamo.backends.cudagraphs import cudagraphs_inner
 from torch._dynamo.testing import same
 from torch._inductor.compile_fx import compile_fx
@@ -13,6 +13,7 @@ from torch._inductor.lowering import lowerings
 from torch._inductor.utils import gen_gm_and_inputs
 from torch.utils._pytree import tree_map_only
 
+
 aten = torch.ops.aten
 
 
diff --git a/benchmarks/dynamo/parse_logs.py b/benchmarks/dynamo/parse_logs.py
index 8ae27289790..9aed78b2e35 100644
--- a/benchmarks/dynamo/parse_logs.py
+++ b/benchmarks/dynamo/parse_logs.py
@@ -3,6 +3,7 @@ import os
 import re
 import sys
 
+
 # This script takes the logs produced by the benchmark scripts (e.g.,
 # torchbench.py) and parses it into a CSV file that summarizes what
 # is failing and why.  It is kept separate from the benchmark script
diff --git a/benchmarks/dynamo/runner.py b/benchmarks/dynamo/runner.py
index bc42b656670..747a8e06e63 100755
--- a/benchmarks/dynamo/runner.py
+++ b/benchmarks/dynamo/runner.py
@@ -23,7 +23,6 @@ If you want to test float16
 
 """
 
-
 import argparse
 import dataclasses
 import functools
@@ -44,7 +43,6 @@ from os.path import abspath, exists
 from random import randint
 
 import matplotlib.pyplot as plt
-
 import numpy as np
 import pandas as pd
 from matplotlib import rcParams
@@ -52,9 +50,9 @@ from scipy.stats import gmean
 from tabulate import tabulate
 
 import torch
-
 import torch._dynamo
 
+
 rcParams.update({"figure.autolayout": True})
 plt.rc("axes", axisbelow=True)
 
diff --git a/benchmarks/dynamo/test.py b/benchmarks/dynamo/test.py
index b2b72b01d97..396f4037f5c 100644
--- a/benchmarks/dynamo/test.py
+++ b/benchmarks/dynamo/test.py
@@ -2,9 +2,9 @@ import os
 import unittest
 
 from .common import parse_args, run
-
 from .torchbench import setup_torchbench_cwd, TorchBenchmarkRunner
 
+
 try:
     # fbcode only
     from aiplatform.utils.sanitizer_status import is_asan_or_tsan
diff --git a/benchmarks/dynamo/timm_models.py b/benchmarks/dynamo/timm_models.py
index 650af586d51..f624e5cd9e8 100755
--- a/benchmarks/dynamo/timm_models.py
+++ b/benchmarks/dynamo/timm_models.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 import importlib
 import logging
 import os
@@ -7,16 +8,17 @@ import subprocess
 import sys
 import warnings
 
+
 try:
     from .common import BenchmarkRunner, download_retry_decorator, main
 except ImportError:
     from common import BenchmarkRunner, download_retry_decorator, main
 
 import torch
-
 from torch._dynamo.testing import collect_results, reduce_to_scalar_loss
 from torch._dynamo.utils import clone_inputs
 
+
 # Enable FX graph caching
 if "TORCHINDUCTOR_FX_GRAPH_CACHE" not in os.environ:
     torch._inductor.config.fx_graph_cache = True
diff --git a/benchmarks/dynamo/torchbench.py b/benchmarks/dynamo/torchbench.py
index bdb5b1a3990..43c2962f9ff 100755
--- a/benchmarks/dynamo/torchbench.py
+++ b/benchmarks/dynamo/torchbench.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 import functools
 import gc
 import importlib
@@ -14,6 +15,7 @@ import yaml
 
 import torch
 
+
 try:
     from .common import BenchmarkRunner, main
 except ImportError:
@@ -22,6 +24,7 @@ except ImportError:
 from torch._dynamo.testing import collect_results, reduce_to_scalar_loss
 from torch._dynamo.utils import clone_inputs
 
+
 # We are primarily interested in tf32 datatype
 torch.backends.cuda.matmul.allow_tf32 = True
 
diff --git a/benchmarks/dynamo/training_loss.py b/benchmarks/dynamo/training_loss.py
index 99e65a45f2a..ff797f07d97 100644
--- a/benchmarks/dynamo/training_loss.py
+++ b/benchmarks/dynamo/training_loss.py
@@ -9,10 +9,10 @@ from datasets import load_dataset, load_metric
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
 import torch
-
 import torch._dynamo
 from torch.utils.data import DataLoader
 
+
 torch.backends.cuda.matmul.allow_tf32 = True
 
 # You will download around 84G dataset if you run this end to end training/evaluation example.
diff --git a/benchmarks/fastrnns/__init__.py b/benchmarks/fastrnns/__init__.py
index 10678d46f03..4b59ea2123d 100644
--- a/benchmarks/fastrnns/__init__.py
+++ b/benchmarks/fastrnns/__init__.py
@@ -1,6 +1,7 @@
 from .cells import *  # noqa: F403
 from .factory import *  # noqa: F403
 
+
 # (output, next_state) = cell(input, state)
 seqLength = 100
 numLayers = 2
diff --git a/benchmarks/fastrnns/conftest.py b/benchmarks/fastrnns/conftest.py
index 1d4e8bbdff7..1ef551e848a 100644
--- a/benchmarks/fastrnns/conftest.py
+++ b/benchmarks/fastrnns/conftest.py
@@ -1,5 +1,6 @@
 import pytest  # noqa: F401
 
+
 default_rnns = [
     "cudnn",
     "aten",
diff --git a/benchmarks/fastrnns/custom_lstms.py b/benchmarks/fastrnns/custom_lstms.py
index 39584624619..0e5643bbeda 100644
--- a/benchmarks/fastrnns/custom_lstms.py
+++ b/benchmarks/fastrnns/custom_lstms.py
@@ -9,6 +9,7 @@ import torch.nn as nn
 from torch import Tensor
 from torch.nn import Parameter
 
+
 """
 Some helper classes for writing custom TorchScript LSTMs.
 
diff --git a/benchmarks/fastrnns/scratch.py b/benchmarks/fastrnns/scratch.py
index 10e5390bfb7..fbd0ebde9e2 100644
--- a/benchmarks/fastrnns/scratch.py
+++ b/benchmarks/fastrnns/scratch.py
@@ -45,6 +45,7 @@ recurrent_scaleshift.graph_for(x, scale, shift)
 
 import torch
 
+
 x = torch.tensor([])
 x.requires_grad = True
 x.mean().backward()  # no error triggered
diff --git a/benchmarks/framework_overhead_benchmark/framework_overhead_benchmark.py b/benchmarks/framework_overhead_benchmark/framework_overhead_benchmark.py
index 826c4d283ee..4a3638e5628 100644
--- a/benchmarks/framework_overhead_benchmark/framework_overhead_benchmark.py
+++ b/benchmarks/framework_overhead_benchmark/framework_overhead_benchmark.py
@@ -1,10 +1,11 @@
 import argparse
 
 from pt_wrapper_module import WrapperModule
-
 from SimpleAddModule import add_tensors_loop, SimpleAddModule
+
 from utils import benchmark_module, BenchmarkConfig, ModuleConfig, ms_to_us
 
+
 """ Framework overhead benchmark script.
 Benchmark framework overhead.
 Currently supported ops: add.
diff --git a/benchmarks/framework_overhead_benchmark/utils.py b/benchmarks/framework_overhead_benchmark/utils.py
index abd8233d5a5..a62f5d4632b 100644
--- a/benchmarks/framework_overhead_benchmark/utils.py
+++ b/benchmarks/framework_overhead_benchmark/utils.py
@@ -3,6 +3,7 @@ from collections import namedtuple
 
 from torch.utils import ThroughputBenchmark
 
+
 NUM_LOOP_ITERS = 1000
 BenchmarkConfig = namedtuple("BenchmarkConfig", "num_warmup_iters num_iters")
 ModuleConfig = namedtuple("ModuleConfig", "pt_fn c2_op num_params graph_mode")
diff --git a/benchmarks/functional_autograd_benchmark/audio_text_models.py b/benchmarks/functional_autograd_benchmark/audio_text_models.py
index 3add9b7e3d5..64b132ab63f 100644
--- a/benchmarks/functional_autograd_benchmark/audio_text_models.py
+++ b/benchmarks/functional_autograd_benchmark/audio_text_models.py
@@ -1,5 +1,4 @@
 import torchaudio_models as models
-
 from utils import check_for_functorch, extract_weights, GetterReturnType, load_weights
 
 import torch
diff --git a/benchmarks/functional_autograd_benchmark/functional_autograd_benchmark.py b/benchmarks/functional_autograd_benchmark/functional_autograd_benchmark.py
index 3a8e90684e7..a78e4d6816e 100644
--- a/benchmarks/functional_autograd_benchmark/functional_autograd_benchmark.py
+++ b/benchmarks/functional_autograd_benchmark/functional_autograd_benchmark.py
@@ -6,6 +6,7 @@ from typing import Any, Callable, List, NamedTuple
 import torch
 from torch.autograd import functional
 
+
 try:
     import functorch as ft
 
diff --git a/benchmarks/functional_autograd_benchmark/torchaudio_models.py b/benchmarks/functional_autograd_benchmark/torchaudio_models.py
index 04dc8969e32..aab5fef96cd 100644
--- a/benchmarks/functional_autograd_benchmark/torchaudio_models.py
+++ b/benchmarks/functional_autograd_benchmark/torchaudio_models.py
@@ -9,6 +9,7 @@ import torch
 import torch.nn.functional as F
 from torch import nn, Tensor
 
+
 __all__ = ["Wav2Letter"]
 
 
diff --git a/benchmarks/functional_autograd_benchmark/torchvision_models.py b/benchmarks/functional_autograd_benchmark/torchvision_models.py
index 66eb23cf4e5..a9ef7e8444b 100644
--- a/benchmarks/functional_autograd_benchmark/torchvision_models.py
+++ b/benchmarks/functional_autograd_benchmark/torchvision_models.py
@@ -4,10 +4,10 @@ from collections import OrderedDict
 
 import torch
 from torch import nn
-
 from torch.jit.annotations import Dict
 from torch.nn import functional as F
 
+
 try:
     from scipy.optimize import linear_sum_assignment
 
diff --git a/benchmarks/functional_autograd_benchmark/utils.py b/benchmarks/functional_autograd_benchmark/utils.py
index b5f79a91f09..87d676f4fb3 100644
--- a/benchmarks/functional_autograd_benchmark/utils.py
+++ b/benchmarks/functional_autograd_benchmark/utils.py
@@ -2,9 +2,9 @@ from collections import defaultdict
 from typing import Callable, Dict, List, Tuple, Union
 
 import torch
-
 from torch import nn, Tensor
 
+
 # Type helpers
 InputsType = Union[Tensor, Tuple[Tensor, ...]]
 # A Getter takes in a device and returns a callable and the inputs to that callable
diff --git a/benchmarks/functional_autograd_benchmark/vision_models.py b/benchmarks/functional_autograd_benchmark/vision_models.py
index fdb06cfcf47..a33ac09da43 100644
--- a/benchmarks/functional_autograd_benchmark/vision_models.py
+++ b/benchmarks/functional_autograd_benchmark/vision_models.py
@@ -1,12 +1,12 @@
 from typing import cast
 
 import torchvision_models as models
-
 from utils import check_for_functorch, extract_weights, GetterReturnType, load_weights
 
 import torch
 from torch import Tensor
 
+
 has_functorch = check_for_functorch()
 
 
diff --git a/benchmarks/fuser/plot_speedups.py b/benchmarks/fuser/plot_speedups.py
index 64dfb0f50d0..c8e4ebfa632 100644
--- a/benchmarks/fuser/plot_speedups.py
+++ b/benchmarks/fuser/plot_speedups.py
@@ -1,5 +1,6 @@
 import pandas
 
+
 df = pandas.read_csv("perf.csv")
 
 ops = pandas.unique(df["operator"])
@@ -11,6 +12,7 @@ pivot_speedups = (pivot_op_shape.T / pivot_op_shape["eager"]).T
 
 import matplotlib.pyplot as plt
 
+
 plt.rcParams["figure.figsize"] = (20, 100)
 fig, axs = plt.subplots(nops)
 plt.subplots_adjust(hspace=0.5)
diff --git a/benchmarks/fuser/run_benchmarks.py b/benchmarks/fuser/run_benchmarks.py
index 40d1b5e9d0f..64b517e1961 100644
--- a/benchmarks/fuser/run_benchmarks.py
+++ b/benchmarks/fuser/run_benchmarks.py
@@ -7,6 +7,7 @@ import click
 
 import torch
 
+
 torch.set_num_threads(1)
 torch._C._debug_set_fusion_group_inlining(False)
 
diff --git a/benchmarks/gpt_fast/benchmark.py b/benchmarks/gpt_fast/benchmark.py
index 5ff277e8f60..cfa1a5424e9 100644
--- a/benchmarks/gpt_fast/benchmark.py
+++ b/benchmarks/gpt_fast/benchmark.py
@@ -10,6 +10,7 @@ import torch
 import torch.nn as nn
 from torch.utils.flop_counter import FlopCounterMode
 
+
 WARMUP_ITER = 5
 
 A100_40G_BF16_TFLOPS = 312
diff --git a/benchmarks/gpt_fast/generate.py b/benchmarks/gpt_fast/generate.py
index c7d0cc6fb0f..c94e1192348 100644
--- a/benchmarks/gpt_fast/generate.py
+++ b/benchmarks/gpt_fast/generate.py
@@ -14,6 +14,7 @@ from quantize import WeightOnlyInt8QuantHandler as LLaMAWeightOnlyInt8QuantHandl
 import torch
 import torch._inductor.config
 
+
 torch._inductor.config.coordinate_descent_tuning = True
 torch._inductor.config.triton.unique_kernel_names = True
 torch._inductor.config.fx_graph_cache = True  # Experimental feature to reduce compilation times, will be on by default in future
diff --git a/benchmarks/gpt_fast/mixtral_moe_quantize.py b/benchmarks/gpt_fast/mixtral_moe_quantize.py
index 6dfac4a9938..c1840330c02 100644
--- a/benchmarks/gpt_fast/mixtral_moe_quantize.py
+++ b/benchmarks/gpt_fast/mixtral_moe_quantize.py
@@ -5,6 +5,7 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
+
 ##### Quantization Primitives ######
 
 
diff --git a/benchmarks/inference/process_metrics.py b/benchmarks/inference/process_metrics.py
index acdd1dffda7..6bd8b5e4faa 100644
--- a/benchmarks/inference/process_metrics.py
+++ b/benchmarks/inference/process_metrics.py
@@ -10,6 +10,7 @@ import os
 
 import pandas as pd
 
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Parse output files")
     parser.add_argument("--csv", type=str, help="Path to csv file")
diff --git a/benchmarks/inference/server.py b/benchmarks/inference/server.py
index 40ef2fd3729..706811b134e 100644
--- a/benchmarks/inference/server.py
+++ b/benchmarks/inference/server.py
@@ -1,5 +1,4 @@
 import argparse
-
 import asyncio
 import os.path
 import subprocess
diff --git a/benchmarks/instruction_counts/core/api.py b/benchmarks/instruction_counts/core/api.py
index 1b7cb48efef..c598e726e97 100644
--- a/benchmarks/instruction_counts/core/api.py
+++ b/benchmarks/instruction_counts/core/api.py
@@ -8,6 +8,7 @@ from typing import Dict, List, Optional, Set, Tuple, TYPE_CHECKING, Union
 
 from worker.main import WorkerTimerArgs
 
+
 if TYPE_CHECKING:
     # Benchmark utils are only partially strict compliant, so MyPy won't follow
     # imports using the public namespace. (Due to an exclusion rule in
diff --git a/benchmarks/instruction_counts/core/expand.py b/benchmarks/instruction_counts/core/expand.py
index 1944aaf00a5..c91b2311c40 100644
--- a/benchmarks/instruction_counts/core/expand.py
+++ b/benchmarks/instruction_counts/core/expand.py
@@ -13,6 +13,7 @@ from typing import List, Optional, Tuple, TYPE_CHECKING
 
 import torch
 
+
 if TYPE_CHECKING:
     # See the note in api.py for why this is necessary.
     from torch.utils.benchmark.utils.timer import Language
diff --git a/benchmarks/instruction_counts/execution/work.py b/benchmarks/instruction_counts/execution/work.py
index c745fde88fa..ab076854e41 100644
--- a/benchmarks/instruction_counts/execution/work.py
+++ b/benchmarks/instruction_counts/execution/work.py
@@ -20,6 +20,7 @@ from worker.main import (
     WorkerUnpickler,
 )
 
+
 if TYPE_CHECKING:
     PopenType = subprocess.Popen[bytes]
 else:
diff --git a/benchmarks/operator_benchmark/benchmark_all_other_test.py b/benchmarks/operator_benchmark/benchmark_all_other_test.py
index f53e8b9d97c..05022e8407f 100644
--- a/benchmarks/operator_benchmark/benchmark_all_other_test.py
+++ b/benchmarks/operator_benchmark/benchmark_all_other_test.py
@@ -1,4 +1,4 @@
-from pt import (  # noqa: F401  # noqa: F401
+from pt import (  # noqa: F401
     add_test,
     ao_sparsifier_test,
     as_strided_test,
@@ -31,5 +31,6 @@ from pt import (  # noqa: F401  # noqa: F401
 
 import operator_benchmark as op_bench
 
+
 if __name__ == "__main__":
     op_bench.benchmark_runner.main()
diff --git a/benchmarks/operator_benchmark/benchmark_all_test.py b/benchmarks/operator_benchmark/benchmark_all_test.py
index 4a364867fbc..f7d967c2c26 100644
--- a/benchmarks/operator_benchmark/benchmark_all_test.py
+++ b/benchmarks/operator_benchmark/benchmark_all_test.py
@@ -4,5 +4,6 @@ from pt import unary_test  # noqa: F401
 
 import operator_benchmark as op_bench
 
+
 if __name__ == "__main__":
     op_bench.benchmark_runner.main()
diff --git a/benchmarks/operator_benchmark/benchmark_core.py b/benchmarks/operator_benchmark/benchmark_core.py
index 241fce8ef5e..bc340ae17f6 100644
--- a/benchmarks/operator_benchmark/benchmark_core.py
+++ b/benchmarks/operator_benchmark/benchmark_core.py
@@ -6,6 +6,7 @@ import timeit
 from collections import namedtuple
 
 import benchmark_utils
+
 import numpy as np
 
 import torch
diff --git a/benchmarks/operator_benchmark/benchmark_runner.py b/benchmarks/operator_benchmark/benchmark_runner.py
index 6abbc566820..0695e4847e7 100644
--- a/benchmarks/operator_benchmark/benchmark_runner.py
+++ b/benchmarks/operator_benchmark/benchmark_runner.py
@@ -1,10 +1,12 @@
 import argparse
 
 import benchmark_core
+
 import benchmark_utils
 
 import torch
 
+
 """Performance microbenchmarks's main binary.
 
 This is the main function for running performance microbenchmark tests.
diff --git a/benchmarks/operator_benchmark/common/repeat_benchmark.py b/benchmarks/operator_benchmark/common/repeat_benchmark.py
index 8f8f5fffb8a..8c0558e3483 100644
--- a/benchmarks/operator_benchmark/common/repeat_benchmark.py
+++ b/benchmarks/operator_benchmark/common/repeat_benchmark.py
@@ -4,6 +4,7 @@ import numpy as np
 
 import torch
 
+
 """Microbenchmarks for Tensor repeat operator. Supports PyTorch."""
 
 input_shapes = (
diff --git a/benchmarks/operator_benchmark/common/tests/jit_forward_test.py b/benchmarks/operator_benchmark/common/tests/jit_forward_test.py
index 339b2856c70..65a86a6c292 100644
--- a/benchmarks/operator_benchmark/common/tests/jit_forward_test.py
+++ b/benchmarks/operator_benchmark/common/tests/jit_forward_test.py
@@ -2,6 +2,7 @@ import operator_benchmark as op_bench
 
 import torch
 
+
 intraop_bench_configs = op_bench.config_list(
     attrs=[
         [8, 16],
diff --git a/benchmarks/operator_benchmark/common/tests/pt_configs_list_test.py b/benchmarks/operator_benchmark/common/tests/pt_configs_list_test.py
index 8e92f5bca18..e5bf5c7800a 100644
--- a/benchmarks/operator_benchmark/common/tests/pt_configs_list_test.py
+++ b/benchmarks/operator_benchmark/common/tests/pt_configs_list_test.py
@@ -2,6 +2,7 @@ import operator_benchmark as op_bench
 
 import torch
 
+
 """Microbenchmarks for element-wise Add operator. Supports both Caffe2/PyTorch."""
 
 add_short_configs = op_bench.config_list(
diff --git a/benchmarks/operator_benchmark/operator_benchmark.py b/benchmarks/operator_benchmark/operator_benchmark.py
index 7121c519fdd..b3c6678420f 100644
--- a/benchmarks/operator_benchmark/operator_benchmark.py
+++ b/benchmarks/operator_benchmark/operator_benchmark.py
@@ -2,4 +2,5 @@
 import benchmark_runner  # noqa: F401
 from benchmark_pytorch import TorchBenchmarkBase  # noqa: F401
 from benchmark_test_generator import *  # noqa: F401,F403
+
 from benchmark_utils import *  # noqa: F401,F403
diff --git a/benchmarks/operator_benchmark/pt/add_test.py b/benchmarks/operator_benchmark/pt/add_test.py
index 8431e4d398d..54504c4f300 100644
--- a/benchmarks/operator_benchmark/pt/add_test.py
+++ b/benchmarks/operator_benchmark/pt/add_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for add_ operator. Supports both Caffe2/PyTorch."""
 
 # Configs for PT add operator
diff --git a/benchmarks/operator_benchmark/pt/ao_sparsifier_test.py b/benchmarks/operator_benchmark/pt/ao_sparsifier_test.py
index a00e0dc3b21..38324edbf3f 100644
--- a/benchmarks/operator_benchmark/pt/ao_sparsifier_test.py
+++ b/benchmarks/operator_benchmark/pt/ao_sparsifier_test.py
@@ -1,7 +1,7 @@
 import operator_benchmark as op_bench
+
 import torch
 from torch import nn
-
 from torch.ao import pruning
 
 
diff --git a/benchmarks/operator_benchmark/pt/batchnorm_test.py b/benchmarks/operator_benchmark/pt/batchnorm_test.py
index 4524c307797..a9f5ffa0b06 100644
--- a/benchmarks/operator_benchmark/pt/batchnorm_test.py
+++ b/benchmarks/operator_benchmark/pt/batchnorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn.functional as F
 
diff --git a/benchmarks/operator_benchmark/pt/binary_test.py b/benchmarks/operator_benchmark/pt/binary_test.py
index a8c9256610d..4a4144a96ee 100644
--- a/benchmarks/operator_benchmark/pt/binary_test.py
+++ b/benchmarks/operator_benchmark/pt/binary_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/bmm_test.py b/benchmarks/operator_benchmark/pt/bmm_test.py
index 3fcdb70cc6a..8ff5d0b5e1b 100644
--- a/benchmarks/operator_benchmark/pt/bmm_test.py
+++ b/benchmarks/operator_benchmark/pt/bmm_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for add_ operator. Supports both Caffe2/PyTorch."""
 
 
diff --git a/benchmarks/operator_benchmark/pt/channel_shuffle_test.py b/benchmarks/operator_benchmark/pt/channel_shuffle_test.py
index 40742b45d3f..a45c790c9f8 100644
--- a/benchmarks/operator_benchmark/pt/channel_shuffle_test.py
+++ b/benchmarks/operator_benchmark/pt/channel_shuffle_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/chunk_test.py b/benchmarks/operator_benchmark/pt/chunk_test.py
index d6c203efe42..7ab456ecb9a 100644
--- a/benchmarks/operator_benchmark/pt/chunk_test.py
+++ b/benchmarks/operator_benchmark/pt/chunk_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/clip_ranges_test.py b/benchmarks/operator_benchmark/pt/clip_ranges_test.py
index 0e4889af44f..5d69c90ba41 100644
--- a/benchmarks/operator_benchmark/pt/clip_ranges_test.py
+++ b/benchmarks/operator_benchmark/pt/clip_ranges_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/configs.py b/benchmarks/operator_benchmark/pt/configs.py
index ccfa62cc364..807182dd592 100644
--- a/benchmarks/operator_benchmark/pt/configs.py
+++ b/benchmarks/operator_benchmark/pt/configs.py
@@ -1,5 +1,6 @@
 import operator_benchmark as op_bench
 
+
 """
 Configs shared by multiple benchmarks
 """
diff --git a/benchmarks/operator_benchmark/pt/conv_test.py b/benchmarks/operator_benchmark/pt/conv_test.py
index ad315d8a0bb..93b4942cea2 100644
--- a/benchmarks/operator_benchmark/pt/conv_test.py
+++ b/benchmarks/operator_benchmark/pt/conv_test.py
@@ -1,9 +1,11 @@
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn as nn
 
+
 """
 Microbenchmarks for Conv1d and ConvTranspose1d operators.
 """
diff --git a/benchmarks/operator_benchmark/pt/diag_test.py b/benchmarks/operator_benchmark/pt/diag_test.py
index bb128a56bfa..9eab6f862bb 100644
--- a/benchmarks/operator_benchmark/pt/diag_test.py
+++ b/benchmarks/operator_benchmark/pt/diag_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/embeddingbag_test.py b/benchmarks/operator_benchmark/pt/embeddingbag_test.py
index f73fbc5425b..d82d6970759 100644
--- a/benchmarks/operator_benchmark/pt/embeddingbag_test.py
+++ b/benchmarks/operator_benchmark/pt/embeddingbag_test.py
@@ -2,8 +2,10 @@ import numpy
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Embedding and EmbeddingBag Operator Benchmark"""
 
 
diff --git a/benchmarks/operator_benchmark/pt/fill_test.py b/benchmarks/operator_benchmark/pt/fill_test.py
index 1252e81982c..4572983a186 100644
--- a/benchmarks/operator_benchmark/pt/fill_test.py
+++ b/benchmarks/operator_benchmark/pt/fill_test.py
@@ -1,8 +1,9 @@
 import operator_benchmark as op_bench
-import torch
 
+import torch
 from torch.testing._internal.common_device_type import get_all_device_types
 
+
 """Microbenchmark for Fill_ operator."""
 
 fill_short_configs = op_bench.config_list(
diff --git a/benchmarks/operator_benchmark/pt/gather_test.py b/benchmarks/operator_benchmark/pt/gather_test.py
index 8a4db487b75..67be175f9c4 100644
--- a/benchmarks/operator_benchmark/pt/gather_test.py
+++ b/benchmarks/operator_benchmark/pt/gather_test.py
@@ -1,6 +1,7 @@
 import numpy
 
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/gelu_test.py b/benchmarks/operator_benchmark/pt/gelu_test.py
index ab83f6659e1..6c48d53738d 100644
--- a/benchmarks/operator_benchmark/pt/gelu_test.py
+++ b/benchmarks/operator_benchmark/pt/gelu_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/groupnorm_test.py b/benchmarks/operator_benchmark/pt/groupnorm_test.py
index ead09808ece..6f033e050c9 100644
--- a/benchmarks/operator_benchmark/pt/groupnorm_test.py
+++ b/benchmarks/operator_benchmark/pt/groupnorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn.functional as F
 
diff --git a/benchmarks/operator_benchmark/pt/hardsigmoid_test.py b/benchmarks/operator_benchmark/pt/hardsigmoid_test.py
index 7e9b51a0c84..27bc02dd2c2 100644
--- a/benchmarks/operator_benchmark/pt/hardsigmoid_test.py
+++ b/benchmarks/operator_benchmark/pt/hardsigmoid_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn as nn
 
diff --git a/benchmarks/operator_benchmark/pt/hardswish_test.py b/benchmarks/operator_benchmark/pt/hardswish_test.py
index d93fe298d2e..82a251a459f 100644
--- a/benchmarks/operator_benchmark/pt/hardswish_test.py
+++ b/benchmarks/operator_benchmark/pt/hardswish_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn as nn
 
diff --git a/benchmarks/operator_benchmark/pt/index_select_test.py b/benchmarks/operator_benchmark/pt/index_select_test.py
index c4a0c233e91..870610071c1 100644
--- a/benchmarks/operator_benchmark/pt/index_select_test.py
+++ b/benchmarks/operator_benchmark/pt/index_select_test.py
@@ -1,6 +1,7 @@
 import numpy
 
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/instancenorm_test.py b/benchmarks/operator_benchmark/pt/instancenorm_test.py
index 47f8243817c..fc74f91bf0f 100644
--- a/benchmarks/operator_benchmark/pt/instancenorm_test.py
+++ b/benchmarks/operator_benchmark/pt/instancenorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn.functional as F
 
diff --git a/benchmarks/operator_benchmark/pt/interpolate_test.py b/benchmarks/operator_benchmark/pt/interpolate_test.py
index 0ae487bc832..c65f0b9c241 100644
--- a/benchmarks/operator_benchmark/pt/interpolate_test.py
+++ b/benchmarks/operator_benchmark/pt/interpolate_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for interpolate operator."""
 
 
diff --git a/benchmarks/operator_benchmark/pt/layernorm_test.py b/benchmarks/operator_benchmark/pt/layernorm_test.py
index 82f12cbaf58..f837a521565 100644
--- a/benchmarks/operator_benchmark/pt/layernorm_test.py
+++ b/benchmarks/operator_benchmark/pt/layernorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn.functional as F
 
diff --git a/benchmarks/operator_benchmark/pt/linear_prepack_fp16_test.py b/benchmarks/operator_benchmark/pt/linear_prepack_fp16_test.py
index e2c72bec92a..582598051e7 100644
--- a/benchmarks/operator_benchmark/pt/linear_prepack_fp16_test.py
+++ b/benchmarks/operator_benchmark/pt/linear_prepack_fp16_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for linear_prepack_fp16_ operator. Supports both Caffe2/PyTorch."""
 
 # Configs for PT linear_prepack_fp16 operator
diff --git a/benchmarks/operator_benchmark/pt/linear_test.py b/benchmarks/operator_benchmark/pt/linear_test.py
index cf7a87f0ec0..6f5e2397545 100644
--- a/benchmarks/operator_benchmark/pt/linear_test.py
+++ b/benchmarks/operator_benchmark/pt/linear_test.py
@@ -1,6 +1,7 @@
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn as nn
 
diff --git a/benchmarks/operator_benchmark/pt/linear_unpack_fp16_test.py b/benchmarks/operator_benchmark/pt/linear_unpack_fp16_test.py
index 3b2ef5bc134..f75642c1f22 100644
--- a/benchmarks/operator_benchmark/pt/linear_unpack_fp16_test.py
+++ b/benchmarks/operator_benchmark/pt/linear_unpack_fp16_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for linear_unpack_fp16_ operator. Supports both Caffe2/PyTorch."""
 
 # Configs for PT linear_unpack_fp16 operator
diff --git a/benchmarks/operator_benchmark/pt/matmul_test.py b/benchmarks/operator_benchmark/pt/matmul_test.py
index 5a2d52e0520..e92728e9ebd 100644
--- a/benchmarks/operator_benchmark/pt/matmul_test.py
+++ b/benchmarks/operator_benchmark/pt/matmul_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for MatMul operator"""
 
 # Configs for PT Matmul operator
diff --git a/benchmarks/operator_benchmark/pt/matrix_mult_test.py b/benchmarks/operator_benchmark/pt/matrix_mult_test.py
index f95c28c663c..c905b566192 100644
--- a/benchmarks/operator_benchmark/pt/matrix_mult_test.py
+++ b/benchmarks/operator_benchmark/pt/matrix_mult_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """
 Microbenchmarks for batch matrix mult with einsum and torch.bmm.
 """
diff --git a/benchmarks/operator_benchmark/pt/pool_test.py b/benchmarks/operator_benchmark/pt/pool_test.py
index 6ac67cece9b..7e842ef649c 100644
--- a/benchmarks/operator_benchmark/pt/pool_test.py
+++ b/benchmarks/operator_benchmark/pt/pool_test.py
@@ -1,7 +1,9 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn as nn
 
+
 """
 Microbenchmarks for MaxPool1d and AvgPool1d operators.
 """
diff --git a/benchmarks/operator_benchmark/pt/qactivation_test.py b/benchmarks/operator_benchmark/pt/qactivation_test.py
index 65e8516a252..9b7280530bc 100644
--- a/benchmarks/operator_benchmark/pt/qactivation_test.py
+++ b/benchmarks/operator_benchmark/pt/qactivation_test.py
@@ -1,7 +1,9 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.nn.quantized.functional as qF
 
+
 r"""Microbenchmarks for the quantized activations."""
 
 qactivation_long_configs = op_bench.cross_product_configs(
diff --git a/benchmarks/operator_benchmark/pt/qarithmetic_test.py b/benchmarks/operator_benchmark/pt/qarithmetic_test.py
index 7a8def81bc5..a65ae561870 100644
--- a/benchmarks/operator_benchmark/pt/qarithmetic_test.py
+++ b/benchmarks/operator_benchmark/pt/qarithmetic_test.py
@@ -1,7 +1,9 @@
 import operator_benchmark as op_bench
+
 import torch
 from torch._ops import ops
 
+
 qarithmetic_binary_configs = op_bench.cross_product_configs(
     N=(2, 8, 64, 512),
     dtype=(torch.quint8, torch.qint8, torch.qint32),
diff --git a/benchmarks/operator_benchmark/pt/qatembedding_ops_test.py b/benchmarks/operator_benchmark/pt/qatembedding_ops_test.py
index 2e72dbe1422..03fc5339610 100644
--- a/benchmarks/operator_benchmark/pt/qatembedding_ops_test.py
+++ b/benchmarks/operator_benchmark/pt/qatembedding_ops_test.py
@@ -2,10 +2,12 @@ import numpy
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.nn.qat as nnqat
 from torch.ao.quantization import default_embedding_qat_qconfig
 
+
 """
 Microbenchmarks for QAT Embedding + EmbeddingBag operators.
 """
diff --git a/benchmarks/operator_benchmark/pt/qbatchnorm_test.py b/benchmarks/operator_benchmark/pt/qbatchnorm_test.py
index b8cee3ae02b..218e133b937 100644
--- a/benchmarks/operator_benchmark/pt/qbatchnorm_test.py
+++ b/benchmarks/operator_benchmark/pt/qbatchnorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/qcomparators_test.py b/benchmarks/operator_benchmark/pt/qcomparators_test.py
index 9a251d6417a..37ee6f60796 100644
--- a/benchmarks/operator_benchmark/pt/qcomparators_test.py
+++ b/benchmarks/operator_benchmark/pt/qcomparators_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 qcomparators_configs = op_bench.cross_product_configs(
     N=(8, 64),
     dtype=(torch.quint8, torch.qint8, torch.qint32),
diff --git a/benchmarks/operator_benchmark/pt/qconv_test.py b/benchmarks/operator_benchmark/pt/qconv_test.py
index 52374acf95b..540480c297c 100644
--- a/benchmarks/operator_benchmark/pt/qconv_test.py
+++ b/benchmarks/operator_benchmark/pt/qconv_test.py
@@ -1,9 +1,11 @@
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.nn.quantized as nnq
 
+
 """
 Microbenchmarks for qConv operators.
 """
diff --git a/benchmarks/operator_benchmark/pt/qembedding_bag_lookups_test.py b/benchmarks/operator_benchmark/pt/qembedding_bag_lookups_test.py
index 7ee0792d1ef..f5fd9dc4ff3 100644
--- a/benchmarks/operator_benchmark/pt/qembedding_bag_lookups_test.py
+++ b/benchmarks/operator_benchmark/pt/qembedding_bag_lookups_test.py
@@ -3,10 +3,11 @@ from typing import Optional
 import numpy as np
 
 import operator_benchmark as op_bench
-import torch
 
+import torch
 from torch.testing._internal.common_quantization import lengths_to_offsets
 
+
 torch.ops.load_library("//caffe2/torch/fb/sparsenn:sparsenn_operators")
 
 
diff --git a/benchmarks/operator_benchmark/pt/qembedding_pack_test.py b/benchmarks/operator_benchmark/pt/qembedding_pack_test.py
index cfc6c51024a..d63b880dc0d 100644
--- a/benchmarks/operator_benchmark/pt/qembedding_pack_test.py
+++ b/benchmarks/operator_benchmark/pt/qembedding_pack_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 embeddingbag_conversion_short_configs = op_bench.cross_product_configs(
     num_embeddings=(80,), embedding_dim=(128, 256, 512), tags=("short",)
 )
diff --git a/benchmarks/operator_benchmark/pt/qembeddingbag_test.py b/benchmarks/operator_benchmark/pt/qembeddingbag_test.py
index fe563af0bc8..adc8c3b2769 100644
--- a/benchmarks/operator_benchmark/pt/qembeddingbag_test.py
+++ b/benchmarks/operator_benchmark/pt/qembeddingbag_test.py
@@ -2,9 +2,11 @@ import numpy
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.nn.quantized as nnq
 
+
 """
 Microbenchmarks for qEmbeddingBag operators.
 """
diff --git a/benchmarks/operator_benchmark/pt/qgroupnorm_test.py b/benchmarks/operator_benchmark/pt/qgroupnorm_test.py
index 0148800450e..73489965e38 100644
--- a/benchmarks/operator_benchmark/pt/qgroupnorm_test.py
+++ b/benchmarks/operator_benchmark/pt/qgroupnorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/qinstancenorm_test.py b/benchmarks/operator_benchmark/pt/qinstancenorm_test.py
index 4dcec4f2a88..196cdea2a11 100644
--- a/benchmarks/operator_benchmark/pt/qinstancenorm_test.py
+++ b/benchmarks/operator_benchmark/pt/qinstancenorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/qinterpolate_test.py b/benchmarks/operator_benchmark/pt/qinterpolate_test.py
index c3afc308f6b..2410266cda8 100644
--- a/benchmarks/operator_benchmark/pt/qinterpolate_test.py
+++ b/benchmarks/operator_benchmark/pt/qinterpolate_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for the quantized interpolate op.
 
 Note: We are not benchmarking `upsample` as it is being deprecated, and calls
diff --git a/benchmarks/operator_benchmark/pt/qlayernorm_test.py b/benchmarks/operator_benchmark/pt/qlayernorm_test.py
index c2015b920d6..0f81497ef60 100644
--- a/benchmarks/operator_benchmark/pt/qlayernorm_test.py
+++ b/benchmarks/operator_benchmark/pt/qlayernorm_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/qlinear_test.py b/benchmarks/operator_benchmark/pt/qlinear_test.py
index 1e96b3a75d1..d90b4e8af64 100644
--- a/benchmarks/operator_benchmark/pt/qlinear_test.py
+++ b/benchmarks/operator_benchmark/pt/qlinear_test.py
@@ -1,10 +1,12 @@
 from pt import configs
 
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.nn.quantized as nnq
 import torch.ao.nn.quantized.dynamic as nnqd
 
+
 """
 Microbenchmarks for Quantized Linear operators.
 """
diff --git a/benchmarks/operator_benchmark/pt/qobserver_test.py b/benchmarks/operator_benchmark/pt/qobserver_test.py
index c4ab625f936..0685a5f01cd 100644
--- a/benchmarks/operator_benchmark/pt/qobserver_test.py
+++ b/benchmarks/operator_benchmark/pt/qobserver_test.py
@@ -1,7 +1,9 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.quantization.observer as obs
 
+
 qobserver_short_configs_dict = {
     "attr_names": ("C", "M", "N", "dtype", "device"),
     "attrs": (
diff --git a/benchmarks/operator_benchmark/pt/qpool_test.py b/benchmarks/operator_benchmark/pt/qpool_test.py
index b2e1118ac89..964a8b54b5c 100644
--- a/benchmarks/operator_benchmark/pt/qpool_test.py
+++ b/benchmarks/operator_benchmark/pt/qpool_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 # 2D pooling will have input matrix of rank 3 or 4
 qpool2d_long_configs = op_bench.config_list(
     attrs=(
diff --git a/benchmarks/operator_benchmark/pt/qrnn_test.py b/benchmarks/operator_benchmark/pt/qrnn_test.py
index 5c4600683f7..6d140464e96 100644
--- a/benchmarks/operator_benchmark/pt/qrnn_test.py
+++ b/benchmarks/operator_benchmark/pt/qrnn_test.py
@@ -1,7 +1,9 @@
 import operator_benchmark as op_bench
+
 import torch
 from torch import nn
 
+
 """
 Microbenchmarks for RNNs.
 """
diff --git a/benchmarks/operator_benchmark/pt/qtensor_method_test.py b/benchmarks/operator_benchmark/pt/qtensor_method_test.py
index 3e545c36874..966c69dd051 100644
--- a/benchmarks/operator_benchmark/pt/qtensor_method_test.py
+++ b/benchmarks/operator_benchmark/pt/qtensor_method_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 # Configs for pointwise and reduction unary ops
 qmethods_configs_short = op_bench.config_list(
     attr_names=["M", "N"],
diff --git a/benchmarks/operator_benchmark/pt/quantization_test.py b/benchmarks/operator_benchmark/pt/quantization_test.py
index 73b0ef09dba..e0d3483963a 100644
--- a/benchmarks/operator_benchmark/pt/quantization_test.py
+++ b/benchmarks/operator_benchmark/pt/quantization_test.py
@@ -1,9 +1,11 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.ao.nn.quantized as nnq
 import torch.ao.quantization as tq
 import torch.nn as nn
 
+
 """Microbenchmarks for general quantization operations."""
 
 # mode is used to show the direction of the benchmark:
diff --git a/benchmarks/operator_benchmark/pt/qunary_test.py b/benchmarks/operator_benchmark/pt/qunary_test.py
index f1f92cbf72c..1f4d08ff579 100644
--- a/benchmarks/operator_benchmark/pt/qunary_test.py
+++ b/benchmarks/operator_benchmark/pt/qunary_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/remainder_test.py b/benchmarks/operator_benchmark/pt/remainder_test.py
index 7b069d4386b..5de8d7ca08d 100644
--- a/benchmarks/operator_benchmark/pt/remainder_test.py
+++ b/benchmarks/operator_benchmark/pt/remainder_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/softmax_test.py b/benchmarks/operator_benchmark/pt/softmax_test.py
index d7c6e170f51..b7fb4bc6dc9 100644
--- a/benchmarks/operator_benchmark/pt/softmax_test.py
+++ b/benchmarks/operator_benchmark/pt/softmax_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 import torch.nn as nn
 
diff --git a/benchmarks/operator_benchmark/pt/split_test.py b/benchmarks/operator_benchmark/pt/split_test.py
index 74c388e4248..4b55626eb9c 100644
--- a/benchmarks/operator_benchmark/pt/split_test.py
+++ b/benchmarks/operator_benchmark/pt/split_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt/sum_test.py b/benchmarks/operator_benchmark/pt/sum_test.py
index 493c950569c..ec9c80222cf 100644
--- a/benchmarks/operator_benchmark/pt/sum_test.py
+++ b/benchmarks/operator_benchmark/pt/sum_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 """Microbenchmarks for sum reduction operator."""
 
 # Configs for PT add operator
diff --git a/benchmarks/operator_benchmark/pt/tensor_to_test.py b/benchmarks/operator_benchmark/pt/tensor_to_test.py
index dfd682e0246..621e58212cb 100644
--- a/benchmarks/operator_benchmark/pt/tensor_to_test.py
+++ b/benchmarks/operator_benchmark/pt/tensor_to_test.py
@@ -1,6 +1,8 @@
 import operator_benchmark as op_bench
+
 import torch
 
+
 tensor_conversion_short_configs = op_bench.cross_product_configs(
     M=(
         8,
diff --git a/benchmarks/operator_benchmark/pt/unary_test.py b/benchmarks/operator_benchmark/pt/unary_test.py
index a5f617fd50c..e605c731396 100644
--- a/benchmarks/operator_benchmark/pt/unary_test.py
+++ b/benchmarks/operator_benchmark/pt/unary_test.py
@@ -1,4 +1,5 @@
 import operator_benchmark as op_bench
+
 import torch
 
 
diff --git a/benchmarks/operator_benchmark/pt_extension/setup.py b/benchmarks/operator_benchmark/pt_extension/setup.py
index 53db50f4436..06bd8bdf235 100644
--- a/benchmarks/operator_benchmark/pt_extension/setup.py
+++ b/benchmarks/operator_benchmark/pt_extension/setup.py
@@ -2,6 +2,7 @@ from setuptools import setup
 
 from torch.utils.cpp_extension import BuildExtension, CppExtension
 
+
 setup(
     name="benchmark_cpp_extension",
     ext_modules=[CppExtension("benchmark_cpp_extension", ["extension.cpp"])],
diff --git a/benchmarks/overrides_benchmark/bench.py b/benchmarks/overrides_benchmark/bench.py
index 72dcf89bedb..1052f252219 100644
--- a/benchmarks/overrides_benchmark/bench.py
+++ b/benchmarks/overrides_benchmark/bench.py
@@ -5,6 +5,7 @@ from common import SubTensor, SubWithTorchFunction, WithTorchFunction
 
 import torch
 
+
 NUM_REPEATS = 1000
 NUM_REPEAT_OF_REPEATS = 1000
 
diff --git a/benchmarks/overrides_benchmark/common.py b/benchmarks/overrides_benchmark/common.py
index fe594bad214..257760ea195 100644
--- a/benchmarks/overrides_benchmark/common.py
+++ b/benchmarks/overrides_benchmark/common.py
@@ -1,5 +1,6 @@
 import torch
 
+
 NUM_REPEATS = 1000
 NUM_REPEAT_OF_REPEATS = 1000
 
diff --git a/benchmarks/overrides_benchmark/pyspybench.py b/benchmarks/overrides_benchmark/pyspybench.py
index 69745162dfe..e7d26660b61 100644
--- a/benchmarks/overrides_benchmark/pyspybench.py
+++ b/benchmarks/overrides_benchmark/pyspybench.py
@@ -4,6 +4,7 @@ from common import SubTensor, SubWithTorchFunction, WithTorchFunction  # noqa: F
 
 import torch
 
+
 Tensor = torch.tensor
 
 NUM_REPEATS = 1000000
diff --git a/benchmarks/profiler_benchmark/profiler_bench.py b/benchmarks/profiler_benchmark/profiler_bench.py
index e29d45f0649..ced82a501cb 100644
--- a/benchmarks/profiler_benchmark/profiler_bench.py
+++ b/benchmarks/profiler_benchmark/profiler_bench.py
@@ -3,9 +3,9 @@ import sys
 import timeit
 
 import torch
-
 from torch.utils.benchmark import Timer
 
+
 PARALLEL_TASKS_NUM = 4
 INTERNAL_ITER = None
 
diff --git a/benchmarks/profiler_benchmark/resnet_memory_profiler.py b/benchmarks/profiler_benchmark/resnet_memory_profiler.py
index 85212b98218..c18d456c83c 100644
--- a/benchmarks/profiler_benchmark/resnet_memory_profiler.py
+++ b/benchmarks/profiler_benchmark/resnet_memory_profiler.py
@@ -1,9 +1,9 @@
 import torchvision.models as models
 
 import torch
-
 import torch.autograd.profiler as profiler
 
+
 for with_cuda in [False, True]:
     model = models.resnet18()
     inputs = torch.randn(5, 3, 224, 224)
diff --git a/benchmarks/serialization/nested_annotation_str.py b/benchmarks/serialization/nested_annotation_str.py
index a7b6cf49cfd..9d14c292031 100644
--- a/benchmarks/serialization/nested_annotation_str.py
+++ b/benchmarks/serialization/nested_annotation_str.py
@@ -1,6 +1,7 @@
 import torch
 import torch.utils.benchmark as benchmark
 
+
 MEMO = {}
 
 
diff --git a/benchmarks/serialization/simple_measurement.py b/benchmarks/serialization/simple_measurement.py
index 9cc12ca1329..ee75acd5a85 100644
--- a/benchmarks/serialization/simple_measurement.py
+++ b/benchmarks/serialization/simple_measurement.py
@@ -2,6 +2,7 @@ from pyarkbench import Benchmark, default_args, Timer
 
 import torch
 
+
 use_new = True
 
 
diff --git a/benchmarks/tensorexpr/__main__.py b/benchmarks/tensorexpr/__main__.py
index 3c80a6e39fe..95e6bd6825a 100644
--- a/benchmarks/tensorexpr/__main__.py
+++ b/benchmarks/tensorexpr/__main__.py
@@ -5,7 +5,7 @@ import os
 # from . import conv           # noqa: F401
 # from . import normalization  # noqa: F401
 # from . import pooling        # noqa: F401
-from . import (  # noqa: F401  # noqa: F401  # noqa: F401  # noqa: F401  # noqa: F401  # noqa: F401  # noqa: F401  # noqa: F401  # noqa: F401
+from . import (  # noqa: F401
     attention,
     benchmark,
     broadcast,
diff --git a/benchmarks/transformer/better_transformer_vs_mha_functional.py b/benchmarks/transformer/better_transformer_vs_mha_functional.py
index 44e8105ef1e..3aa2e6c214c 100644
--- a/benchmarks/transformer/better_transformer_vs_mha_functional.py
+++ b/benchmarks/transformer/better_transformer_vs_mha_functional.py
@@ -12,7 +12,6 @@ import argparse
 import itertools
 import json
 import random
-
 import warnings
 from collections import defaultdict, OrderedDict
 from pathlib import Path
@@ -20,12 +19,12 @@ from pprint import pprint
 from typing import Optional
 
 import numpy as np
-
 from prettytable import PrettyTable
 from tqdm import tqdm
 
 import torch
 
+
 warnings.filterwarnings("ignore")
 
 error_dict = defaultdict(int)
diff --git a/benchmarks/transformer/score_mod.py b/benchmarks/transformer/score_mod.py
index 040838d0786..d8a88f2a2b3 100644
--- a/benchmarks/transformer/score_mod.py
+++ b/benchmarks/transformer/score_mod.py
@@ -13,6 +13,7 @@ import torch
 import torch.nn.functional as F
 from torch.nn.attention.flex_attention import flex_attention
 
+
 torch._dynamo.config.automatic_dynamic_shapes = False
 # Needed since changing args to function causes recompiles
 torch._dynamo.config.cache_size_limit = 1000
diff --git a/benchmarks/transformer/sdp.py b/benchmarks/transformer/sdp.py
index eacf6cf0f00..3edda07b309 100644
--- a/benchmarks/transformer/sdp.py
+++ b/benchmarks/transformer/sdp.py
@@ -1,7 +1,6 @@
 import argparse
 import itertools
 import random
-
 import warnings
 from dataclasses import dataclass
 from pathlib import Path
@@ -16,6 +15,7 @@ import torch
 import torch.utils.benchmark as benchmark
 from torch.backends.cuda import sdp_kernel
 
+
 warnings.filterwarnings("ignore")
 
 
diff --git a/tools/linter/adapters/ufmt_linter.py b/tools/linter/adapters/ufmt_linter.py
index 203811bc6e4..851d80afbbe 100644
--- a/tools/linter/adapters/ufmt_linter.py
+++ b/tools/linter/adapters/ufmt_linter.py
@@ -32,7 +32,6 @@ ISORT_WHITELIST = re.compile(
                     # .ci/**
                     # .github/**
                     # benchmarks/**
-                    "benchmarks/**",
                     # functorch/**
                     "functorch/**",
                     # tools/**