llama-stack-mirror/llama_stack
Dinesh Yeduguru 57a9b4d57f
Allow models to be registered as long as llama model is provided (#472)
This PR allows models to be registered with provider as long as the user
specifies a llama model, even though the model does not match our
prebuilt provider specific mapping.
Test:
pytest -v -s
llama_stack/providers/tests/inference/test_model_registration.py -m
"together" --env TOGETHER_API_KEY=<KEY>

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
2024-11-18 15:05:29 -08:00
..
apis No more model_id warnings 2024-11-15 12:20:18 -08:00
cli Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00
distribution Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00
providers Allow models to be registered as long as llama model is provided (#472) 2024-11-18 15:05:29 -08:00
scripts Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00
templates Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00