Dinesh Yeduguru 8b8d1c1ef4 fix trace starting in library client (#655) ... # What does this PR do? Because of the way library client sets up async io boundaries, tracing was broken with streaming. This PR fixes the tracing to start at the right way to caputre the life time of async gen functions correctly. Test plan: Script ran: https://gist.github.com/yanxi0830/f6645129e55ab12de3cd6ec71564c69e Before: No spans returned for a session Now: We see spans <img width="1678" alt="Screenshot 2024-12-18 at 9 50 46 PM" src="https://github.com/user-attachments/assets/58a3b0dd-a41c-489a-b89a-075e698a2c03" />		2024-12-19 16:13:52 -08:00
..
apis	Register Message and ResponseFormat	2024-12-18 10:32:25 -08:00
cli	doc: llama-stack build --config help text references old directory (#596)	2024-12-10 17:42:02 -08:00
distribution	fix trace starting in library client (#655)	2024-12-19 16:13:52 -08:00
providers	Fixed imports for inference (#661)	2024-12-19 14:19:36 -08:00
scripts	Fix to conda env build script	2024-12-17 12:19:34 -08:00
templates	[4/n][torchtune integration] support lazy load model during inference (#620)	2024-12-18 16:30:53 -08:00
__init__.py	export LibraryClient	2024-12-13 12:08:00 -08:00