mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
156bfa0e15
* fix non-streaming api in inference server * unit test for inline inference * Added non-streaming ollama inference impl * add streaming support for ollama inference with tests * addressing comments --------- Co-authored-by: Hardik Shah <hjshah@fb.com>
22 lines
726 B
Python
22 lines
726 B
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# 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
|
|
|
|
|
|
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 OllamaInference(config.impl_config)
|
|
|
|
from .client import InferenceClient
|
|
|
|
return InferenceClient(config.impl_config.url)
|