biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/executor/cpu_executor.py
View File

@@ -109,12 +109,14 @@ 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]],
num_lookahead_slots: int,
) -> 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,
blocks_to_swap_out=blocks_to_swap_out,
blocks_to_copy=blocks_to_copy)
blocks_to_copy=blocks_to_copy,
num_lookahead_slots=num_lookahead_slots)
return output
async def check_health_async(self) -> None: