[BugFix][V1] Fix parallel sampling finishing/aborts (#14512)

Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-12 13:29:48 -04:00
parent 916836bbfb
commit f5d3acd474
7 changed files with 137 additions and 113 deletions
--- a/vllm/v1/engine/llm_engine.py
+++ b/vllm/v1/engine/llm_engine.py
@@ -137,8 +137,8 @@ class LLMEngine:
    def abort_request(self, request_ids: list[str]) -> None:
        """Remove request_ids from EngineCore and Detokenizer."""

+        request_ids = self.output_processor.abort_requests(request_ids)
        self.engine_core.abort_requests(request_ids)
-        self.output_processor.abort_requests(request_ids)

    def add_request(
        self,