forked from phoenix-oss/llama-stack-mirror
b2b00a216b
# What does this PR do? switch sambanova inference adaptor to LiteLLM usage to simplify integration and solve issues with current adaptor when streaming and tool calling, models and templates updated ## Test Plan pytest -s -v tests/integration/inference/test_text_inference.py --stack-config=sambanova --text-model=sambanova/Meta-Llama-3.3-70B-Instruct pytest -s -v tests/integration/inference/test_vision_inference.py --stack-config=sambanova --vision-model=sambanova/Llama-3.2-11B-Vision-Instruct
18 lines
607 B
Python
18 lines
607 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 llama_stack.apis.inference import Inference
|
|
|
|
from .config import SambaNovaImplConfig
|
|
|
|
|
|
async def get_adapter_impl(config: SambaNovaImplConfig, _deps) -> Inference:
|
|
from .sambanova import SambaNovaInferenceAdapter
|
|
|
|
assert isinstance(config, SambaNovaImplConfig), f"Unexpected config type: {type(config)}"
|
|
impl = SambaNovaInferenceAdapter(config)
|
|
await impl.initialize()
|
|
return impl
|