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, 23:30 UTC
[Bugfix] Ensure LoRA path from the request can be included in err msg (#13450)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Yuan Tang committed
Feb 18, 2025 at 03:19 UTC
e2603fefb8c0bc1195e68d1e83f1099ecebfea4c
1 file changed
+1
-1
vllm/lora/worker_manager.py
+1
-1
@@ -133,7 +133,7 @@ class WorkerLoRAManager(AbstractWorkerManager):
133
# For NotFoundError
134
raise ValueError(
135
f"Loading lora {lora_request.lora_name} failed: No adapter "
136
- f"found for {lora_path}") from e
136
+ f"found for {lora_request.lora_path}") from e
137
except Exception as e:
138
# For BadRequestError
139
raise e