precommit

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.
+# the root directory of this source tree.

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(

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,

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
 
 

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
 
 

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