Ben Browning c014571258 fix: OpenAI API - together.ai extra usage chunks ... 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>		2025-04-13 13:39:56 -04:00
..
__init__.py	add NVIDIA NIM inference adapter (#355)	2024-11-23 15:59:00 -08:00
config.py	chore: move all Llama Stack types from llama-models to llama-stack (#1098)	2025-02-14 09:10:59 -08:00
models.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
nvidia.py	fix: OpenAI API - together.ai extra usage chunks	2025-04-13 13:39:56 -04:00
openai_utils.py	refactor: move all llama code to models/llama out of meta reference (#1887)	2025-04-07 15:03:58 -07:00
utils.py	style: remove prints in codebase (#1146)	2025-02-18 19:41:37 -08:00