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 4, 03:45 UTC
[Bugfix] Fix FusedMoEWithLoRA has no attribute `runner` (#41889)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Jee Jee Li committed
May 7, 2026 at 19:53 UTC
9c0812ffd0ea66cd50109019b289e39194e17a16
1 file changed
+4
vllm/lora/layers/fused_moe.py
+4
@@ -335,6 +335,10 @@ class FusedMoEWithLoRA(BaseLayerWithLoRA):
335
def quant_method(self):
336
return self.base_layer.quant_method
337
338
+ @property
339
+ def runner(self):
340
+ return self.base_layer.runner
341
+
342
@property
343
def is_internal_router(self) -> bool:
344
return self.base_layer.is_internal_router