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

precommit

Browse source
This commit is contained in:
Xi Yan 2024-11-08 17:58:58 -08:00
parent 1ebf6447c5
commit ba82021d4b
11 changed files with 19 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -28,13 +28,13 @@ from fairscale.nn.model_parallel.initialize import (
get_model_parallel_src_rank,
)
from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
from pydantic import BaseModel, Field
from torch.distributed.launcher.api import elastic_launch, LaunchConfig
from typing_extensions import Annotated
from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
from .generation import TokenResult