[BugFix] fix num_lookahead_slots missing in async executor (#4165)

Co-authored-by: Lei Wen <wenlei03@qiyi.com>
2024-05-01 01:12:59 +08:00
parent 26f2fb5113
commit 4bb53e2dde
9 changed files with 163 additions and 19 deletions
--- a/vllm/executor/ray_gpu_executor.py
+++ b/vllm/executor/ray_gpu_executor.py
@@ -196,6 +196,7 @@ class RayGPUExecutor(DistributedGPUExecutor):
                "blocks_to_swap_in": blocks_to_swap_in,
                "blocks_to_swap_out": blocks_to_swap_out,
                "blocks_to_copy": blocks_to_copy,
+                "num_lookahead_slots": num_lookahead_slots,
            },
            use_ray_compiled_dag=USE_RAY_COMPILED_DAG)