phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 03:29:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: OpenAI API - together.ai extra usage chunks

Browse source 
This fixes an issue where, with some models (ie the Llama 4 models),
together.ai is sending a final usage chunk for streaming responses
even if the user didn't ask to include usage.

With this change, the OpenAI API verification tests now pass 100% when
using Llama Stack as your API server and together.ai as the backend
provider.

As part of this, I also cleaned up the streaming/non-streaming return
types of the `openai_chat_completion` method to keep type checking happy.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-04-12 17:27:43 -04:00
parent a4b573d750
commit c014571258
12 changed files with 153 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/passthrough/passthrough.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
from llama_stack_client import AsyncLlamaStackClient
@ -28,6 +28,7 @@ from llama_stack.apis.inference import (
)
from llama_stack.apis.inference.inference import (
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAICompletion,
OpenAIMessageParam,
OpenAIResponseFormatParam,
@ -282,7 +283,7 @@ class PassthroughInferenceAdapter(Inference):
top_logprobs: Optional[int] = None,
top_p: Optional[float] = None,
user: Optional[str] = None,
) -> OpenAIChatCompletion:
) -> Union[OpenAIChatCompletion, AsyncIterator[OpenAIChatCompletionChunk]]:
client = self._get_client()
model_obj = await self.model_store.get_model(model)