phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 04:17:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

models endpoint testing

Browse source
This commit is contained in:
Xi Yan 2024-09-22 00:01:35 -07:00
parent c0199029e5
commit 0348f26e00
10 changed files with 235 additions and 79 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/adapters/inference/together/together.py
View file

@ -42,7 +42,14 @@ class TogetherInferenceAdapter(Inference):
async def shutdown(self) -> None:
pass
async def completion(self, request: CompletionRequest) -> AsyncGenerator:
async def completion(
self,
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
raise NotImplementedError()
def _messages_to_together_messages(self, messages: list[Message]) -> list: