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

Add an option to not use elastic agents for meta-reference inference (#269)

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 12:51:10 -07:00 • committed by GitHub
parent be3c5c034d
commit 33afd34e6f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 33 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/impls/meta_reference/inference/config.py
View file

@ -17,13 +17,18 @@ from llama_stack.providers.utils.inference import supported_inference_models
class MetaReferenceInferenceConfig(BaseModel):
model: str = Field(
default="Llama3.1-8B-Instruct",
default="Llama3.2-3B-Instruct",
description="Model descriptor from `llama model list`",
)
torch_seed: Optional[int] = None
max_seq_len: int = 4096
max_batch_size: int = 1
# when this is False, we assume that the distributed process group is setup by someone
# outside of this code (e.g., when run inside `torchrun`). that is useful for clients
# (including our testing code) who might be using llama-stack as a library.
create_distributed_process_group: bool = True
@field_validator("model")
@classmethod
def validate_model(cls, model: str) -> str: