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, 06:00 UTC
[Frontend] Remove unreachable code from llm.py (#19288)
Signed-off-by: KsuParkhamchuk <k.parkhamchuk@gmail.com>
Kseniya Parkhamchuk committed
Jun 8, 2025 at 21:22 UTC
8335667c22f1ae53923d85f810581c10df03a125
1 file changed
-1
vllm/entrypoints/llm.py
-1
@@ -519,7 +519,6 @@ class LLM:
519
Sequence) and len(lora_request) != len(prompts):
520
raise ValueError(
521
"Lora request list should be the same length as the prompts")
522
- return lora_request
522
523
if lora_request is None or isinstance(lora_request, LoRARequest):
524
return [lora_request] * len(prompts)