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 12, 01:00 UTC
Fix broken multiline assert in `LoRAModelManager.register_module` (#30032)
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
Yongtao Huang committed
Dec 4, 2025 at 22:04 UTC
dd97e047e03f5218bddf05fa71f0592df0b8e30e
1 file changed
+2
-2
vllm/lora/models.py
+2
-2
@@ -574,9 +574,9 @@ class LoRAModelManager:
574
575
def register_module(self, module_name: str, module: "BaseLayerWithLoRA"):
576
assert isinstance(module, BaseLayerWithLoRA), (
577
- f"Module {module_name} must be a BaseLayerWithLoRA instance,"
577
+ f"Module {module_name} must be a BaseLayerWithLoRA instance, "
578
+ f"got {type(module)}"
579
)
579
- f" got {type(module)}"
580
self.modules[module_name] = module
581
582
def create_dummy_lora(