[V1] Avoid redundant input processing in n>1 case (#14985)

Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-20 22:24:10 -07:00
parent 7297941b38
commit da6ea29f7a
13 changed files with 85 additions and 145 deletions
--- a/vllm/engine/llm_engine.py
+++ b/vllm/engine/llm_engine.py
@@ -783,7 +783,6 @@ class LLMEngine:

        preprocessed_inputs = self.input_preprocessor.preprocess(
            prompt,
-            request_id=request_id,
            lora_request=lora_request,
            prompt_adapter_request=prompt_adapter_request,
        )