phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 12:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into inference_refactor

Browse source
This commit is contained in:
Botao Chen 2024-12-16 16:47:57 -08:00
commit 6a51e2268d
117 changed files with 12698 additions and 2589 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/distribution/routers/routers.py
View file

@ -111,7 +111,7 @@ class InferenceRouter(Inference):
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
if model.model_type == ModelType.embedding_model:
if model.model_type == ModelType.embedding:
raise ValueError(
f"Model '{model_id}' is an embedding model and does not support chat completions"
)
@ -144,7 +144,7 @@ class InferenceRouter(Inference):
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
if model.model_type == ModelType.embedding_model:
if model.model_type == ModelType.embedding:
raise ValueError(
f"Model '{model_id}' is an embedding model and does not support chat completions"
)