phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 21:47:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Memory tests pass now

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-15 20:55:06 -08:00
parent e51154964f
commit 59ce047aea
23 changed files with 122 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -114,7 +114,7 @@ class VLLMInferenceImpl(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,
@ -218,8 +218,6 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
yield chunk
async def embeddings(
self, model_id: str, contents: list[InterleavedTextMedia]
self, model_id: str, contents: List[InterleavedContent]
) -> EmbeddingsResponse:
log.info("vLLM embeddings")
# TODO
raise NotImplementedError()