phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 11:12:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

working fireworks and together

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 13:07:35 -08:00
parent 25d8ab0e14
commit 8de4cee373
8 changed files with 205 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/distribution/routers/routers.py
View file

@ -105,9 +105,8 @@ class InferenceRouter(Inference):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.routing_table.get_model(model_id)
params = dict(
model_id=model.provider_resource_id,
model_id=model_id,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
@ -132,10 +131,9 @@ class InferenceRouter(Inference):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.routing_table.get_model(model_id)
provider = self.routing_table.get_provider_impl(model_id)
params = dict(
model_id=model.provider_resource_id,
model_id=model_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
@ -152,9 +150,8 @@ class InferenceRouter(Inference):
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse:
model = await self.routing_table.get_model(model_id)
return await self.routing_table.get_provider_impl(model_id).embeddings(
model_id=model.provider_resource_id,
model_id=model_id,
contents=contents,
)