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 14, 05:30 UTC
[Misc] code clean duplicate set_current_vllm_config in _set_vllm_config (#22566)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Aug 10, 2025 at 15:08 UTC
326976291b541f0fd5bef34aa1ff4a84bf8fb37d
1 file changed
-1
tests/kernels/moe/modular_kernel_tools/parallel_utils.py
-1
@@ -36,7 +36,6 @@ def _set_vllm_config(vllm_config: VllmConfig, world_size: int, rank: int,
36
import tempfile
37
temp_file = tempfile.mkstemp()[1]
38
39
- set_current_vllm_config(vllm_config)
39
with set_current_vllm_config(vllm_config):
40
init_distributed_environment(
41
world_size=world_size,