mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-05 12:21:52 +00:00
models routing work
This commit is contained in:
parent
f3ff3a3001
commit
9bdd4e3dd9
3 changed files with 20 additions and 3 deletions
|
@ -98,7 +98,13 @@ class OllamaInferenceAdapter(Inference):
|
|||
stream: Optional[bool] = False,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
) -> AsyncGenerator:
|
||||
cprint("!! calling remote ollama !!", "red")
|
||||
cprint("!! calling remote ollama {}, url={}!!".format(model, self.url), "red")
|
||||
yield ChatCompletionResponseStreamChunk(
|
||||
event=ChatCompletionResponseEvent(
|
||||
event_type=ChatCompletionResponseEventType.start,
|
||||
delta="",
|
||||
)
|
||||
)
|
||||
# request = ChatCompletionRequest(
|
||||
# model=model,
|
||||
# messages=messages,
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue