[BugFix] Fix return type of executor execute_model methods (#4402)

2024-04-27 11:17:45 -07:00
parent d6e520e170
commit ba4be44c32
6 changed files with 9 additions and 8 deletions
--- a/vllm/executor/cpu_executor.py
+++ b/vllm/executor/cpu_executor.py
@@ -109,7 +109,7 @@ class CPUExecutorAsync(CPUExecutor, ExecutorAsyncBase):
        blocks_to_swap_in: Dict[int, int],
        blocks_to_swap_out: Dict[int, int],
        blocks_to_copy: Dict[int, List[int]],
-    ) -> SamplerOutput:
+    ) -> List[SamplerOutput]:
        output = await make_async(self.driver_worker.execute_model)(
            seq_group_metadata_list=seq_group_metadata_list,
            blocks_to_swap_in=blocks_to_swap_in,