llama-stack-mirror/llama_stack/providers/utils/inference
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
..
__init__.py Allow models to be registered as long as llama model is provided (#472) 2024-11-18 15:05:29 -08:00
model_registry.py Allow models to be registered as long as llama model is provided (#472) 2024-11-18 15:05:29 -08:00
openai_compat.py Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) (#376) 2024-11-05 16:22:33 -08:00
prompt_adapter.py Inference to use provider resource id to register and validate (#428) 2024-11-12 20:02:00 -08:00