phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 22:29:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temp commit

Browse source
This commit is contained in:
Botao Chen 2024-12-16 16:44:15 -08:00
parent de44af1501
commit 35b1a6f2dc
7 changed files with 54 additions and 113 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/inference/meta_reference/config.py
View file

@ -16,7 +16,9 @@ from llama_stack.providers.utils.inference import supported_inference_models
class MetaReferenceInferenceConfig(BaseModel):
model: Optional[str] = None
model: Optional[str] = (
None # this is a placeholder to indicate inference model id, not actually being used
)
torch_seed: Optional[int] = None
max_seq_len: int = 4096
max_batch_size: int = 1