phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

test: verification on provider's OAI endpoints (#1893)

Browse source 
# What does this PR do?


## Test Plan
export MODEL=accounts/fireworks/models/llama4-scout-instruct-basic;
LLAMA_STACK_CONFIG=verification pytest -s -v tests/integration/inference
--vision-model $MODEL --text-model $MODEL
This commit is contained in:
ehhuang 2025-04-07 23:06:28 -07:00 • committed by GitHub
parent 530d4bdfe1
commit 7b4eb0967e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 1683 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/providers/utils/inference/model_registry.py
View file

@ -33,12 +33,17 @@ def get_huggingface_repo(model_descriptor: str) -> Optional[str]:
return None
def build_hf_repo_model_entry(provider_model_id: str, model_descriptor: str) -> ProviderModelEntry:
def build_hf_repo_model_entry(
provider_model_id: str, model_descriptor: str, additional_aliases: Optional[List[str]] = None
) -> ProviderModelEntry:
aliases = [
get_huggingface_repo(model_descriptor),
]
if additional_aliases:
aliases.extend(additional_aliases)
return ProviderModelEntry(
provider_model_id=provider_model_id,
aliases=[
get_huggingface_repo(model_descriptor),
],
aliases=aliases,
llama_model=model_descriptor,
)