phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add note about use of together.AsyncTogether for model listing

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-16 14:24:01 -04:00
parent 1e5c84e99c
commit c9c402e418
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/remote/inference/together/together.py
View file

@ -261,6 +261,7 @@ class TogetherInferenceAdapter(OpenAIMixin, ModelRegistryHelper, Inference, Need
async def list_models(self) -> list[Model] | None: async def list_models(self) -> list[Model] | None:
self._model_cache = {} self._model_cache = {}
# Together's /v1/models is not compatible with OpenAI's /v1/models. Together support ticket #13355 -> will not fix, use Together's own client
for m in await self._get_client().models.list(): for m in await self._get_client().models.list():
if m.type == "embedding": if m.type == "embedding":
if m.id not in EMBEDDING_MODEL_ENTRIES: if m.id not in EMBEDDING_MODEL_ENTRIES: