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
@@ -34,7 +34,12 @@ def _can_p2p(rank: int, world_size: int) -> bool:
continue
if envs.VLLM_SKIP_P2P_CHECK:
logger.debug("Skipping P2P check and trusting the driver's P2P report.")
return torch.cuda.can_device_access_peer(rank, i)
# can_device_access_peer takes visible device ordinals, while
# rank and i are logical local IDs.
return torch.cuda.can_device_access_peer(
current_platform.logical_device_id_to_visible_device_id(rank),
current_platform.logical_device_id_to_visible_device_id(i),
)
if not gpu_p2p_access_check(rank, i):
return False
return True
@@ -126,13 +131,10 @@ class CustomAllreduce:
CUSTOM_ALL_REDUCE_MAX_SIZES[device_capability_str][world_size],
max_size,
)
cuda_visible_devices = envs.CUDA_VISIBLE_DEVICES
if cuda_visible_devices:
device_ids = list(map(int, cuda_visible_devices.split(",")))
else:
device_ids = list(range(current_platform.device_count()))
physical_device_id = device_ids[device.index]
# device.index is a visible ordinal, not a logical local ID.
physical_device_id = current_platform.visible_device_id_to_physical_device_id(
device.index
)
tensor = torch.tensor([physical_device_id], dtype=torch.int, device="cpu")
gather_list = [
torch.tensor([0], dtype=torch.int, device="cpu") for _ in range(world_size)