phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make all API methods async def again

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 16:50:57 -07:00
parent 95a96afe34
commit 627edaf407
17 changed files with 120 additions and 145 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/distribution/routers/routers.py
View file

@ -70,7 +70,7 @@ class InferenceRouter(Inference):
async def register_model(self, model: ModelDef) -> None:
await self.routing_table.register_model(model)
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -93,11 +93,11 @@ class InferenceRouter(Inference):
)
provider = self.routing_table.get_provider_impl(model)
if stream:
return (chunk async for chunk in provider.chat_completion(**params))
return (chunk async for chunk in await provider.chat_completion(**params))
else:
return provider.chat_completion(**params)
return await provider.chat_completion(**params)
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -114,9 +114,9 @@ class InferenceRouter(Inference):
logprobs=logprobs,
)
if stream:
return (chunk async for chunk in provider.completion(**params))
return (chunk async for chunk in await provider.completion(**params))
else:
return provider.completion(**params)
return await provider.completion(**params)
async def embeddings(
self,