phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Added non-streaming ollama inference impl

Browse source
This commit is contained in:
Hardik Shah 2024-07-30 18:11:44 -07:00
parent 5b9c05c5dd
commit 0e75e73fa7
4 changed files with 332 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_toolchain/inference/api_instance.py
View file

@ -12,6 +12,10 @@ async def get_inference_api_instance(config: InferenceConfig):
from .inference import InferenceImpl
return InferenceImpl(config.impl_config)
elif config.impl_config.impl_type == ImplType.ollama.value:
from .inference import OllamaInference
return OllamaInference(config.impl_config)
from .client import InferenceClient