replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

Signed-off-by: Liao, Wei <wei.liao@intel.com>
Signed-off-by: wliao2 <wei.liao@intel.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
wliao2
2026-03-31 22:32:54 +08:00
committed by GitHub
co-authored by Harry Mellor Kunshang Ji
parent e8057c00bc
commit 4dfad17ed1
20 changed files with 96 additions and 92 deletions
@@ -17,7 +17,6 @@ from vllm.distributed.device_communicators.all_reduce_utils import (
from vllm.distributed.parallel_state import in_the_same_node_as
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.utils.torch_utils import cuda_device_count_stateless
try:
ops.meta_size()
@@ -135,7 +134,7 @@ class CustomAllreduce:
if cuda_visible_devices:
device_ids = list(map(int, cuda_visible_devices.split(",")))
else:
device_ids = list(range(cuda_device_count_stateless()))
device_ids = list(range(current_platform.device_count()))
physical_device_id = device_ids[device.index]
tensor = torch.tensor([physical_device_id], dtype=torch.int, device="cpu")