squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Core][Distributed] improve logging for init dist (#4042)

Browse Source
This commit is contained in:
youkaichao 2024-04-13 07:12:53 -07:00 committed by GitHub
parent 5c2e66e487
commit 98afde19fc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/distributed/parallel_state.py
View File

@ -8,6 +8,10 @@ from typing import Optional
import torch import torch
from vllm.logger import init_logger
logger = init_logger(__name__)
# Tensor model parallel group that the current rank belongs to. # Tensor model parallel group that the current rank belongs to.
_TENSOR_MODEL_PARALLEL_GROUP = None _TENSOR_MODEL_PARALLEL_GROUP = None
# Pipeline model parallel group that the current rank belongs to. # Pipeline model parallel group that the current rank belongs to.
@ -45,6 +49,8 @@ def init_distributed_environment(
local_rank: int = -1, local_rank: int = -1,
backend: str = "nccl", backend: str = "nccl",
): ):
logger.debug(f"{world_size=} {rank=} {local_rank=} "
f"{distributed_init_method=} {backend=}")
if not torch.distributed.is_initialized(): if not torch.distributed.is_initialized():
assert distributed_init_method is not None, ( assert distributed_init_method is not None, (
"distributed_init_method must be provided when initializing " "distributed_init_method must be provided when initializing "