From 25bee275ebcefe5e531b557771421c9a7906c771 Mon Sep 17 00:00:00 2001 From: Xi Yan Date: Fri, 27 Dec 2024 11:26:14 -0800 Subject: [PATCH] meta reference import --- .../inline/inference/meta_reference/generation.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/llama_stack/providers/inline/inference/meta_reference/generation.py b/llama_stack/providers/inline/inference/meta_reference/generation.py index 9067fb043..1807e4ad5 100644 --- a/llama_stack/providers/inline/inference/meta_reference/generation.py +++ b/llama_stack/providers/inline/inference/meta_reference/generation.py @@ -36,7 +36,12 @@ from llama_models.sku_list import resolve_model from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData from pydantic import BaseModel -from llama_stack.apis.inference import ResponseFormat, ResponseFormatType +from llama_stack.apis.inference import ( + Fp8QuantizationConfig, + Int4QuantizationConfig, + ResponseFormat, + ResponseFormatType, +) from llama_stack.distribution.utils.model_utils import model_local_dir from llama_stack.providers.utils.inference.prompt_adapter import ( @@ -44,12 +49,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import ( CompletionRequestWithRawContent, ) -from .config import ( - Fp8QuantizationConfig, - Int4QuantizationConfig, - MetaReferenceInferenceConfig, - MetaReferenceQuantizedInferenceConfig, -) +from .config import MetaReferenceInferenceConfig, MetaReferenceQuantizedInferenceConfig log = logging.getLogger(__name__)