diff --git a/llama_stack/providers/inline/agents/meta_reference/config.py b/llama_stack/providers/inline/agents/meta_reference/config.py
index 8ade558c3..2770ed13c 100644
--- a/llama_stack/providers/inline/agents/meta_reference/config.py
+++ b/llama_stack/providers/inline/agents/meta_reference/config.py
@@ -4,9 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from pydantic import BaseModel, Field
+
 from llama_stack.providers.utils.kvstore import KVStoreConfig
 from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
-from pydantic import BaseModel, Field
 
 
 class MetaReferenceAgentsImplConfig(BaseModel):
diff --git a/llama_stack/providers/inline/agents/meta_reference/persistence.py b/llama_stack/providers/inline/agents/meta_reference/persistence.py
index 36ae9b367..37ac75d6a 100644
--- a/llama_stack/providers/inline/agents/meta_reference/persistence.py
+++ b/llama_stack/providers/inline/agents/meta_reference/persistence.py
@@ -11,9 +11,10 @@ from datetime import datetime
 
 from typing import List, Optional
 from llama_stack.apis.agents import *  # noqa: F403
-from llama_stack.providers.utils.kvstore import KVStore
 from pydantic import BaseModel
 
+from llama_stack.providers.utils.kvstore import KVStore
+
 
 class AgentSessionInfo(BaseModel):
     session_id: str
diff --git a/llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py b/llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py
index 3b303f5bd..b668dc0d6 100644
--- a/llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py
+++ b/llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py
@@ -10,13 +10,14 @@ from jinja2 import Template
 from llama_models.llama3.api import *  # noqa: F403
 
 
+from termcolor import cprint  # noqa: F401
+
 from llama_stack.apis.agents import (
     DefaultMemoryQueryGeneratorConfig,
     LLMMemoryQueryGeneratorConfig,
     MemoryQueryGenerator,
     MemoryQueryGeneratorConfig,
 )
-from termcolor import cprint  # noqa: F401
 from llama_stack.apis.inference import *  # noqa: F403
 
 
diff --git a/llama_stack/providers/inline/inference/__init__.py b/llama_stack/providers/inline/inference/__init__.py
index 6f3c1df03..756f351d8 100644
--- a/llama_stack/providers/inline/inference/__init__.py
+++ b/llama_stack/providers/inline/inference/__init__.py
@@ -2,4 +2,4 @@
 # All rights reserved.
 #
 # This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
\ No newline at end of file
+# the root directory of this source tree.
diff --git a/llama_stack/providers/inline/inference/meta_reference/config.py b/llama_stack/providers/inline/inference/meta_reference/config.py
index 6ecba22b0..48cba645b 100644
--- a/llama_stack/providers/inline/inference/meta_reference/config.py
+++ b/llama_stack/providers/inline/inference/meta_reference/config.py
@@ -10,9 +10,10 @@ from llama_models.datatypes import *  # noqa: F403
 from llama_models.sku_list import resolve_model
 
 from llama_stack.apis.inference import *  # noqa: F401, F403
-from llama_stack.providers.utils.inference import supported_inference_models
 from pydantic import BaseModel, Field, field_validator
 
+from llama_stack.providers.utils.inference import supported_inference_models
+
 
 class MetaReferenceInferenceConfig(BaseModel):
     model: str = Field(
diff --git a/llama_stack/providers/inline/inference/meta_reference/generation.py b/llama_stack/providers/inline/inference/meta_reference/generation.py
index 8d6a14fc9..2f296c7c2 100644
--- a/llama_stack/providers/inline/inference/meta_reference/generation.py
+++ b/llama_stack/providers/inline/inference/meta_reference/generation.py
@@ -35,12 +35,13 @@ from termcolor import cprint
 
 from llama_stack.apis.inference import *  # noqa: F403
 
+from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
+
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.utils.inference.prompt_adapter import (
     augment_content_with_response_format_prompt,
     chat_completion_request_to_messages,
 )
-from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
 
 from .config import (
     Fp8QuantizationConfig,
diff --git a/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py b/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py
index 470b6b1ca..62eeefaac 100644
--- a/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py
+++ b/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py
@@ -28,13 +28,13 @@ from fairscale.nn.model_parallel.initialize import (
     get_model_parallel_src_rank,
 )
 
-from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
-
 from pydantic import BaseModel, Field
 
 from torch.distributed.launcher.api import elastic_launch, LaunchConfig
 from typing_extensions import Annotated
 
+from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
+
 from .generation import TokenResult
 
 
diff --git a/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py b/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py
index 286224931..3eaac1e71 100644
--- a/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py
+++ b/llama_stack/providers/inline/inference/meta_reference/quantization/loader.py
@@ -21,13 +21,13 @@ from llama_models.llama3.api.args import ModelArgs
 from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
 from llama_models.sku_list import resolve_model
 
-from llama_stack.apis.inference import QuantizationType
-
 from termcolor import cprint
 from torch import nn, Tensor
 
 from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
 
+from llama_stack.apis.inference import QuantizationType
+
 from ..config import MetaReferenceQuantizedInferenceConfig
 
 
diff --git a/llama_stack/providers/inline/inference/vllm/config.py b/llama_stack/providers/inline/inference/vllm/config.py
index 22b439f77..a7469ebde 100644
--- a/llama_stack/providers/inline/inference/vllm/config.py
+++ b/llama_stack/providers/inline/inference/vllm/config.py
@@ -5,9 +5,9 @@
 # the root directory of this source tree.
 
 from llama_models.schema_utils import json_schema_type
+from pydantic import BaseModel, Field, field_validator
 
 from llama_stack.providers.utils.inference import supported_inference_models
-from pydantic import BaseModel, Field, field_validator
 
 
 @json_schema_type
diff --git a/llama_stack/providers/inline/memory/faiss/config.py b/llama_stack/providers/inline/memory/faiss/config.py
index fd26272ae..41970b05f 100644
--- a/llama_stack/providers/inline/memory/faiss/config.py
+++ b/llama_stack/providers/inline/memory/faiss/config.py
@@ -5,13 +5,13 @@
 # the root directory of this source tree.
 
 from llama_models.schema_utils import json_schema_type
+from pydantic import BaseModel
 
 from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
 from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
-from pydantic import BaseModel
 
 
 @json_schema_type
diff --git a/llama_stack/providers/inline/memory/faiss/faiss.py b/llama_stack/providers/inline/memory/faiss/faiss.py
index 5726d6f87..c362eeedb 100644
--- a/llama_stack/providers/inline/memory/faiss/faiss.py
+++ b/llama_stack/providers/inline/memory/faiss/faiss.py
@@ -8,11 +8,11 @@ import logging
 
 from typing import Any, Dict, List, Optional
 
+import faiss
+
 import numpy as np
 from numpy.typing import NDArray
 
-import faiss
-
 from llama_models.llama3.api.datatypes import *  # noqa: F403
 
 from llama_stack.apis.memory import *  # noqa: F403