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, 02:15 UTC
[Bugfix] : Fix typo - logger.warn_once -> logger.warning_once (#20852)
Varun Sundar Rabindranath committed
Jul 12, 2025 at 07:56 UTC
890323dc1b1141c816637af960208678a30588b6
1 file changed
+1
-1
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py
+1
-1
@@ -111,7 +111,7 @@ class PplxPrepareAndFinalize(mk.FusedMoEPrepareAndFinalize):
111
# topk_indices_dtype() int32
112
#
113
if expert_map is not None:
114
- logger.warn_once(
114
+ logger.warning_once(
115
"The PPLX backend does not support expert mapping. "
116
"The provided `expert_map` will be ignored.")
117
expert_map = None #noqa: F841