phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 04:45:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use huggingface_hub inference client for TGI inference

Browse source
This commit is contained in:
Celina Hanouti 2024-09-05 18:29:04 +02:00
parent 21bedc1596
commit e5bcfdac21
6 changed files with 179 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_toolchain/inference/adapters/tgi/__init__.py
View file

@ -4,12 +4,15 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from llama_toolchain.core.datatypes import RemoteProviderConfig
from .config import TGIImplConfig
async def get_adapter_impl(config: RemoteProviderConfig, _deps):
from .tgi import TGIInferenceAdapter
async def get_adapter_impl(config: TGIImplConfig, _deps):
from .tgi import TGIAdapter
impl = TGIInferenceAdapter(config.url)
assert isinstance(
config, TGIImplConfig
), f"Unexpected config type: {type(config)}"
impl = TGIAdapter(config)
await impl.initialize()
return impl