phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 10:22:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pre-commit

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-25 12:58:17 -07:00
parent d0b6894a41
commit cd39509e56
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/impls/meta_reference/inference/generation.py
View file

@ -35,11 +35,12 @@ from termcolor import cprint
from llama_stack.apis.inference import * # noqa: F403 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.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 (
chat_completion_request_to_messages, chat_completion_request_to_messages,
) )
from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
from .config import ( from .config import (
Fp8QuantizationConfig, Fp8QuantizationConfig,