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

Co-authored-by: Lei Wen <wenlei03@qiyi.com>
This commit is contained in:
leiwen83
2024-05-01 01:12:59 +08:00
committed by GitHub
parent 26f2fb5113
commit 4bb53e2dde
9 changed files with 163 additions and 19 deletions

View File

@@ -211,9 +211,11 @@ class _AsyncLLMEngine(LLMEngine):
if not scheduler_outputs.is_empty():
# Execute the model.
output = await self.model_executor.execute_model_async(
seq_group_metadata_list, scheduler_outputs.blocks_to_swap_in,
seq_group_metadata_list,
scheduler_outputs.blocks_to_swap_in,
scheduler_outputs.blocks_to_swap_out,
scheduler_outputs.blocks_to_copy)
scheduler_outputs.blocks_to_copy,
num_lookahead_slots=scheduler_outputs.num_lookahead_slots)
else:
output = []