pre-commit lint

llama_stack/apis/inference/event_logger.py

@@ -4,11 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from termcolor import cprint
+
 from llama_stack.apis.inference import (
     ChatCompletionResponseEventType,
     ChatCompletionResponseStreamChunk,
 )
-from termcolor import cprint
 
 
 class LogEvent:

llama_stack/cli/model/describe.py

@@ -9,12 +9,12 @@ import json
 
 from llama_models.sku_list import resolve_model
 
+from termcolor import colored
+
 from llama_stack.cli.subcommand import Subcommand
 from llama_stack.cli.table import print_table
 from llama_stack.distribution.utils.serialize import EnumEncoder
 
-from termcolor import colored
-
 
 class ModelDescribe(Subcommand):
     """Show details about a model"""

llama_stack/cli/stack/run.py

@@ -46,6 +46,7 @@ class StackRun(Subcommand):
 
         import pkg_resources
         import yaml
+
         from llama_stack.distribution.build import ImageType
         from llama_stack.distribution.utils.config_dirs import BUILDS_BASE_DIR
 

llama_stack/distribution/configure.py

@@ -9,6 +9,10 @@ from typing import Any
 from pydantic import BaseModel
 
 from llama_stack.distribution.datatypes import *  # noqa: F403
+from prompt_toolkit import prompt
+from prompt_toolkit.validation import Validator
+from termcolor import cprint
+
 from llama_stack.apis.memory.memory import MemoryBankType
 from llama_stack.distribution.distribution import (
     api_providers,
@@ -21,9 +25,6 @@ from llama_stack.distribution.utils.prompt_for_config import prompt_for_config
 from llama_stack.providers.impls.meta_reference.safety.config import (
     MetaReferenceShieldType,
 )
-from prompt_toolkit import prompt
-from prompt_toolkit.validation import Validator
-from termcolor import cprint
 
 
 def make_routing_entry_type(config_class: Any):

llama_stack/distribution/server/server.py

@@ -435,13 +435,13 @@ def main(yaml_config: str, port: int = 5000, disable_ipv6: bool = False):
         apis_to_serve = set(config.apis_to_serve)
     else:
         apis_to_serve = set(impls.keys())
-    
+
     for api_str in apis_to_serve:
         api = Api(api_str)
 
         endpoints = all_endpoints[api]
         impl = impls[api]
-        
+
         provider_spec = specs[api]
         if (
             isinstance(provider_spec, RemoteProviderSpec)

llama_stack/distribution/utils/config_dirs.py

@@ -8,7 +8,9 @@ import os
 from pathlib import Path
 
 
-LLAMA_STACK_CONFIG_DIR = Path(os.getenv("LLAMA_STACK_CONFIG_DIR", os.path.expanduser("~/.llama/")))
+LLAMA_STACK_CONFIG_DIR = Path(
+    os.getenv("LLAMA_STACK_CONFIG_DIR", os.path.expanduser("~/.llama/"))
+)
 
 DISTRIBS_BASE_DIR = LLAMA_STACK_CONFIG_DIR / "distributions"
 

llama_stack/distribution/utils/dynamic.py

@@ -8,7 +8,6 @@ import importlib
 from typing import Any, Dict
 
 from llama_stack.distribution.datatypes import *  # noqa: F403
-from termcolor import cprint
 
 
 def instantiate_class_type(fully_qualified_name):

llama_stack/providers/adapters/inference/together/together.py

@@ -15,10 +15,10 @@ from llama_models.sku_list import resolve_model
 from together import Together
 
 from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.distribution.request_headers import get_request_provider_data
 from llama_stack.providers.utils.inference.augment_messages import (
     augment_messages_for_tools,
 )
-from llama_stack.distribution.request_headers import get_request_provider_data
 
 from .config import TogetherImplConfig
 

llama_stack/providers/impls/meta_reference/inference/quantization/loader.py

@@ -14,6 +14,10 @@ import torch
 
 from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
 from llama_models.llama3.api.model import Transformer, TransformerBlock
+
+from termcolor import cprint
+from torch import Tensor
+
 from llama_stack.apis.inference import QuantizationType
 
 from llama_stack.apis.inference.config import (
@@ -21,9 +25,6 @@ from llama_stack.apis.inference.config import (
     MetaReferenceImplConfig,
 )
 
-from termcolor import cprint
-from torch import Tensor
-
 
 def is_fbgemm_available() -> bool:
     try: