Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)

Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: kourosh hakhamaneshi <kouroshHakha@users.noreply.github.com>
This commit is contained in:
Tyler Michael Smith
2026-06-20 13:38:10 -07:00
committed by GitHub
co-authored by Claude Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> kourosh hakhamaneshi
parent e9de72fe6c
commit ebfbcfe46a
24 changed files with 722 additions and 185 deletions
+19 -3
View File
@@ -86,6 +86,15 @@ class StatelessGroupCoordinator(GroupCoordinator):
self.rank = global_rank
self.local_rank = local_rank
from vllm.distributed.parallel_state import _WORLD
if _WORLD is not None:
self.device_index = _WORLD.device_index
else:
assert local_rank >= 0, (
"local_rank must be provided when creating the world group"
)
self.device_index = local_rank
self_device_group = None
self_cpu_group = None
@@ -152,11 +161,18 @@ class StatelessGroupCoordinator(GroupCoordinator):
self.tcp_store_group = self_tcp_store_group
if current_platform.is_cuda_alike():
self.device = torch.device(f"cuda:{local_rank}")
visible_device_index = (
current_platform.logical_device_id_to_visible_device_id(
self.device_index
)
)
self.device = torch.device(f"cuda:{visible_device_index}")
elif current_platform.is_xpu():
self.device = torch.device(f"xpu:{local_rank}")
self.device = torch.device(f"xpu:{self.device_index}")
elif current_platform.is_out_of_tree():
self.device = torch.device(f"{current_platform.device_name}:{local_rank}")
self.device = torch.device(
f"{current_platform.device_name}:{self.device_index}"
)
else:
self.device = torch.device("cpu")