Skip to content
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

[Bugfix] No num_gpus for ROCm and XPU when connecting to a ray cluster #8781

Closed
wants to merge 1 commit into from
Closed

[Bugfix] No num_gpus for ROCm and XPU when connecting to a ray cluster #8781

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
9 changes: 2 additions & 7 deletions vllm/executor/ray_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.sequence import ExecuteModelRequest, IntermediateTensors
from vllm.utils import get_ip, is_hip
from vllm.utils import get_ip
from vllm.worker.worker_base import WorkerWrapperBase

logger = init_logger(__name__)
Expand Down Expand Up @@ -231,12 +231,7 @@ def initialize_ray_cluster(
assert_ray_available()

# Connect to a ray cluster.
if is_hip() or current_platform.is_xpu():
ray.init(address=ray_address,
ignore_reinit_error=True,
num_gpus=parallel_config.world_size)
else:
ray.init(address=ray_address, ignore_reinit_error=True)
ray.init(address=ray_address, ignore_reinit_error=True)

if parallel_config.placement_group:
# Placement group is already set.
Expand Down