phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename ModelInference to Inference

Browse source
This commit is contained in:
rsm 2024-07-21 12:19:52 -07:00
parent 245461620d
commit 67f0510edd
18 changed files with 468 additions and 1636 deletions
Download patch file Download diff file Expand all files Collapse all files

10
toolchain/inference/server.py
View file

@ -11,7 +11,7 @@ from fastapi.responses import StreamingResponse
from omegaconf import OmegaConf
from toolchain.utils import get_default_config_dir, parse_config
from .api.config import ModelInferenceHydraConfig
from .api.config import InferenceHydraConfig
from .api.endpoints import ChatCompletionRequest, ChatCompletionResponseStreamChunk
from .api_instance import get_inference_api_instance
@ -43,13 +43,13 @@ async def startup():
global InferenceApiInstance
config = get_config()
hydra_config = ModelInferenceHydraConfig(
**OmegaConf.to_container(config["model_inference_config"], resolve=True)
hydra_config = InferenceHydraConfig(
**OmegaConf.to_container(config["inference_config"], resolve=True)
)
model_inference_config = hydra_config.convert_to_model_inferene_config()
inference_config = hydra_config.convert_to_inference_config()
InferenceApiInstance = await get_inference_api_instance(
model_inference_config,
inference_config,
)
await InferenceApiInstance.initialize()