phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 21:39:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tests pass with Ollama now

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-15 17:31:21 -08:00
parent a9a041a1de
commit e51154964f
27 changed files with 83 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -83,7 +83,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def completion(
self,
model_id: str,
content: InterleavedTextMedia,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
@ -267,7 +267,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def embeddings(
self,
model_id: str,
contents: List[InterleavedTextMedia],
contents: List[InterleavedContent],
) -> EmbeddingsResponse:
raise NotImplementedError()