phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 13:49:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-nvidia-inference-adapter

Browse source
This commit is contained in:
Matthew Farrellee 2024-11-21 06:49:13 -05:00
commit 5fbfb9d854
92 changed files with 2145 additions and 678 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/utils/inference/__init__.py
View file

@ -22,9 +22,9 @@ def is_supported_safety_model(model: Model) -> bool:
]
def supported_inference_models() -> List[str]:
def supported_inference_models() -> List[Model]:
return [
m.descriptor()
m
for m in all_registered_models()
if (
m.model_family in {ModelFamily.llama3_1, ModelFamily.llama3_2}

4
llama_stack/providers/utils/inference/prompt_adapter.py
View file

@ -178,7 +178,9 @@ def chat_completion_request_to_messages(
cprint(f"Could not resolve model {llama_model}", color="red")
return request.messages
if model.descriptor() not in supported_inference_models():
allowed_models = supported_inference_models()
descriptors = [m.descriptor() for m in allowed_models]
if model.descriptor() not in descriptors:
cprint(f"Unsupported inference model? {model.descriptor()}", color="red")
return request.messages