phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 17:29:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

meta reference import

Browse source
This commit is contained in:
Xi Yan 2024-12-27 11:26:14 -08:00
parent db49fc8ad0
commit 25bee275eb
1 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/inline/inference/meta_reference/generation.py
View file

@ -36,7 +36,12 @@ from llama_models.sku_list import resolve_model
from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
from pydantic import BaseModel 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.distribution.utils.model_utils import model_local_dir
from llama_stack.providers.utils.inference.prompt_adapter import ( from llama_stack.providers.utils.inference.prompt_adapter import (
@ -44,12 +49,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
CompletionRequestWithRawContent, CompletionRequestWithRawContent,
) )
from .config import ( from .config import MetaReferenceInferenceConfig, MetaReferenceQuantizedInferenceConfig
Fp8QuantizationConfig,
Int4QuantizationConfig,
MetaReferenceInferenceConfig,
MetaReferenceQuantizedInferenceConfig,
)
log = logging.getLogger(__name__) log = logging.getLogger(__name__)