xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:04:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Always set RAY_ADDRESS for Ray actor before spawn (#21540)

Browse Source 
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
This commit is contained in:
Rui Qiao 2025-07-25 17:08:30 -07:00 committed by GitHub
parent cea96a0156
commit c7742d6113
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
vllm/utils/__init__.py
View File

@ -2883,26 +2883,27 @@ def _maybe_force_spawn():
if os.environ.get("VLLM_WORKER_MULTIPROC_METHOD") == "spawn":
return
reason = None
if cuda_is_initialized():
reason = "CUDA is initialized"
elif xpu_is_initialized():
reason = "XPU is initialized"
elif is_in_ray_actor():
reasons = []
if is_in_ray_actor():
# even if we choose to spawn, we need to pass the ray address
# to the subprocess so that it knows how to connect to the ray cluster.
# env vars are inherited by subprocesses, even if we use spawn.
import ray
os.environ["RAY_ADDRESS"] = ray.get_runtime_context().gcs_address
reason = "In a Ray actor and can only be spawned"
reasons.append("In a Ray actor and can only be spawned")
if reason is not None:
if cuda_is_initialized():
reasons.append("CUDA is initialized")
elif xpu_is_initialized():
reasons.append("XPU is initialized")
if reasons:
logger.warning(
"We must use the `spawn` multiprocessing start method. "
"Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. "
"See https://docs.vllm.ai/en/latest/usage/"
"troubleshooting.html#python-multiprocessing "
"for more information. Reason: %s", reason)
"for more information. Reasons: %s", "; ".join(reasons))
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"