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

Distribution server now functioning

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-02 13:37:40 -07:00
parent 041cafbee3
commit 2cf9915806
21 changed files with 635 additions and 266 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_toolchain/inference/api_instance.py
View file

@ -4,19 +4,19 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from .api.config import ImplType, InferenceConfig
# from .api.config import ImplType, InferenceConfig
async def get_inference_api_instance(config: InferenceConfig):
if config.impl_config.impl_type == ImplType.inline.value:
from .inference import InferenceImpl
# async def get_inference_api_instance(config: InferenceConfig):
# if config.impl_config.impl_type == ImplType.inline.value:
# from .inference import InferenceImpl
return InferenceImpl(config.impl_config)
elif config.impl_config.impl_type == ImplType.ollama.value:
from .ollama import OllamaInference
# return InferenceImpl(config.impl_config)
# elif config.impl_config.impl_type == ImplType.ollama.value:
# from .ollama import OllamaInference
return OllamaInference(config.impl_config)
# return OllamaInference(config.impl_config)
from .client import InferenceClient
# from .client import InferenceClient
return InferenceClient(config.impl_config.url)
# return InferenceClient(config.impl_config.url)