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
[Bugfix] Add missing 'is_internal_router' attribute to FusedMoEWithLoRA (#27351)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Oct 22, 2025 at 23:19 UTC
9771e0b4322c3e8675938a934a019e2f17f82d9f
1 file changed
+4
vllm/lora/layers/fused_moe.py
+4
@@ -405,3 +405,7 @@ class FusedMoEWithLoRA(BaseLayerWithLoRA):
405
@property
406
def quant_method(self):
407
return self.base_layer.quant_method
408
+
409
+ @property
410
+ def is_internal_router(self) -> bool:
411
+ return self.base_layer.is_internal_router