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
@@ -482,10 +482,11 @@ def _init_lmcache_engine(
)
# Change current device.
num_gpus = torch.accelerator.device_count()
local_rank = parallel_config.rank % num_gpus
torch.accelerator.set_device_index(local_rank)
device = torch.device(f"cuda:{local_rank}")
from vllm.distributed.parallel_state import get_world_group
device_index = get_world_group().device_index
torch.accelerator.set_device_index(device_index)
device = torch.device(f"cuda:{device_index}")
metadata = LMCacheEngineMetadata(
model_config.model,
parallel_config.world_size,