Skip to content

[XPU] Make pp group initilized for pipeline-parallelism #11648

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 7, 2025
Merged

[XPU] Make pp group initilized for pipeline-parallelism #11648

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions vllm/worker/xpu_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
from vllm.config import VllmConfig
from vllm.distributed import (ensure_model_parallel_initialized,
init_distributed_environment)
from vllm.distributed.parallel_state import get_pp_group
from vllm.logger import init_logger
from vllm.model_executor import set_random_seed
from vllm.platforms import current_platform
Expand Down Expand Up @@ -176,3 +177,8 @@ def init_worker_distributed_environment(self) -> None:
parallel_config.pipeline_parallel_size)
# global all_reduce needed for overall oneccl warm up
torch.distributed.all_reduce(torch.zeros(1).xpu())

if parallel_config.pipeline_parallel_size > 1:
# Add pp group init to avoid
# p2p communication as the first call
get_pp_group().all_reduce(torch.zeros(1).xpu())
Loading