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

refactor: move generation.py to llama3

Browse source
This commit is contained in:
Ashwin Bharambe 2025-03-03 13:38:06 -08:00
parent 02066591b8
commit 816fdf289a
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/inline/inference/meta_reference/model_parallel.py
View file

@ -18,8 +18,9 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
CompletionRequestWithRawContent,
)
from .common import model_checkpoint_dir
from .config import MetaReferenceInferenceConfig
from .generation import Llama, model_checkpoint_dir
from .llama3.generation import Llama3
from .parallel_utils import ModelParallelProcessGroup
@ -42,7 +43,7 @@ def init_model_cb(
model_id: str,
llama_model: Model,
):
llama = Llama.build(config, model_id, llama_model)
llama = Llama3.build(config, model_id, llama_model)
return ModelRunner(llama)