vllm/vllm/env_override.py
youkaichao 1cab43c2d2
[misc] instruct pytorch to use nvml-based cuda check (#15951)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-04-03 01:02:58 +08:00

22 lines
748 B
Python

# SPDX-License-Identifier: Apache-2.0
import os
import torch
# set some common config/environment variables that should be set
# for all processes created by vllm and all processes
# that interact with vllm workers.
# they are executed whenever `import vllm` is called.
# see https://github.com/NVIDIA/nccl/issues/1234
os.environ['NCCL_CUMEM_ENABLE'] = '0'
# see https://github.com/vllm-project/vllm/pull/15951
# it avoids unintentional cuda initialization from torch.cuda.is_available()
os.environ['PYTORCH_NVML_BASED_CUDA_CHECK'] = '1'
# see https://github.com/vllm-project/vllm/issues/10480
os.environ['TORCHINDUCTOR_COMPILE_THREADS'] = '1'
# see https://github.com/vllm-project/vllm/issues/10619
torch._inductor.config.compile_threads = 1