phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Add provider deprecation support; change directory structure (#397)

Browse source 
* Add provider deprecation support; change directory structure

* fix a couple dangling imports

* move the meta_reference safety dir also
This commit is contained in:
Ashwin Bharambe 2024-11-07 13:04:53 -08:00 • committed by GitHub
parent 36e2538eb0
commit 694c142b89
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
58 changed files with 61 additions and 120 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/providers/inline/inference/vllm/__init__.py Normal file
View file

@ -0,0 +1,17 @@
# 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 typing import Any
from .config import VLLMConfig
async def get_provider_impl(config: VLLMConfig, _deps) -> Any:
from .vllm import VLLMInferenceImpl
impl = VLLMInferenceImpl(config)
await impl.initialize()
return impl