phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki 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 725423c95c
commit 02066591b8
4 changed files with 46 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -55,7 +55,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
)
from .config import MetaReferenceInferenceConfig
from .generation import Llama
from .llama3.generation import Llama3
from .model_parallel import LlamaModelParallelGenerator
log = logging.getLogger(__name__)
@ -83,7 +83,7 @@ class MetaReferenceInferenceImpl(
self.generator = LlamaModelParallelGenerator(self.config, model_id, llama_model)
self.generator.start()
else:
self.generator = Llama.build(self.config, model_id, llama_model)
self.generator = Llama3.build(self.config, model_id, llama_model)
self.model_id = model_id
self.llama_model = llama_model