A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 06:00 UTC
[Misc] Reduce warning message introduced in env_override (#19476)
Signed-off-by: Lu Fang <lufang@fb.com>
Lu Fang committed
Jun 11, 2025 at 17:29 UTC
871d6b7c744962aa6f1a468fb05f880b41a39c9e
1 file changed
+1
-1
vllm/env_override.py
+1
-1
@@ -13,7 +13,7 @@ logger = init_logger(__name__)
13
# that interact with vllm workers.
14
# they are executed whenever `import vllm` is called.
15
16
-if 'NCCL_CUMEM_ENABLE' in os.environ:
16
+if os.environ.get('NCCL_CUMEM_ENABLE', '0') != '0':
17
logger.warning(
18
"NCCL_CUMEM_ENABLE is set to %s, skipping override. "
19
"This may increase memory overhead with cudagraph+allreduce: "