fix: register provider model name and HF alias in run.yaml (#1304)

Each model known to the system has two identifiers: 

- the `provider_resource_id` (what the provider calls it) -- e.g.,
`accounts/fireworks/models/llama-v3p1-8b-instruct`
- the `identifier` (`model_id`) under which it is registered and gets
routed to the appropriate provider.

We have so far used the HuggingFace repo alias as the standardized
identifier you can use to refer to the model. So in the above example,
we'd use `meta-llama/Llama-3.1-8B-Instruct` as the name under which it
gets registered. This makes it convenient for users to refer to these
models across providers.

However, we forgot to register the _actual_ provider model ID also. You
should be able to route via `provider_resource_id` also, of course.

This change fixes this (somewhat grave) omission.

*Note*: this change is additive -- more aliases work now compared to
before.

## Test Plan

Run the following for distro=(ollama fireworks together)
```
LLAMA_STACK_CONFIG=$distro \
   pytest -s -v tests/client-sdk/inference/test_text_inference.py \
   --inference-model=meta-llama/Llama-3.1-8B-Instruct --vision-inference-model=""
```
This commit is contained in:
Ashwin Bharambe 2025-02-27 16:39:23 -08:00 committed by GitHub
parent c54164556a
commit 04de2f84e9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
49 changed files with 637 additions and 217 deletions

View file

@ -47,7 +47,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.prompt_adapter import content_has_media
from . import NVIDIAConfig
from .models import _MODEL_ENTRIES
from .models import MODEL_ENTRIES
from .openai_utils import (
convert_chat_completion_request,
convert_completion_request,
@ -62,7 +62,7 @@ logger = logging.getLogger(__name__)
class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
def __init__(self, config: NVIDIAConfig) -> None:
# TODO(mf): filter by available models
ModelRegistryHelper.__init__(self, model_entries=_MODEL_ENTRIES)
ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)
logger.info(f"Initializing NVIDIAInferenceAdapter({config.url})...")