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, 23:45 UTC
[Misc] Fix duplicate FusedMoEConfig debug messages (#21455)
Signed-off-by: Nick Hill <nhill@redhat.com>
Nick Hill committed
Jul 24, 2025 at 09:27 UTC
f0f4de8f2640cf112ffc167da74a7ac905e3dc84
1 file changed
+2
-2
vllm/model_executor/layers/fused_moe/config.py
+2
-2
@@ -325,8 +325,8 @@ class FusedMoEConfig:
325
326
def __post_init__(self):
327
if self.dp_size > 1:
328
- logger.debug("Using FusedMoEConfig::max_num_tokens=%d",
329
- self.max_num_tokens)
328
+ logger.debug_once("Using FusedMoEConfig::max_num_tokens=%d",
329
+ self.max_num_tokens)
330
331
assert self.max_num_tokens > 0
332