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 16, 02:00 UTC
[DOC] Add missing docstring in LLMEngine.add_request() (#12195)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Yuan Tang committed
Jan 20, 2025 at 01:59 UTC
d2643128f7741b937435b00fecde7d6b2e351d0c
1 file changed
+2
vllm/engine/llm_engine.py
+2
@@ -689,7 +689,9 @@ class LLMEngine:
689
:class:`~vllm.PoolingParams` for pooling.
690
arrival_time: The arrival time of the request. If None, we use
691
the current monotonic time.
692
+ lora_request: The LoRA request to add.
693
trace_headers: OpenTelemetry trace headers.
694
+ prompt_adapter_request: The prompt adapter request to add.
695
priority: The priority of the request.
696
Only applicable with priority scheduling.
697