Skip to content
This repository was archived by the owner on Oct 11, 2024. It is now read-only.

Commit eb2af39

Browse files
youkaichaoRobert Shaw
authored andcommitted
[Bugfix] fix type hint for py 3.8 (vllm-project#4036)
1 parent 1f045c7 commit eb2af39

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

vllm/executor/executor_base.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
from abc import ABC, abstractmethod
2-
from typing import Dict, List, Optional
2+
from typing import Dict, List, Optional, Tuple
33

44
from vllm.config import (CacheConfig, DeviceConfig, LoRAConfig, ModelConfig,
55
ParallelConfig, SchedulerConfig, SpeculativeConfig,
@@ -31,7 +31,7 @@ def __init__(
3131
raise NotImplementedError
3232

3333
@abstractmethod
34-
def determine_num_available_blocks(self) -> tuple[int, int]:
34+
def determine_num_available_blocks(self) -> Tuple[int, int]:
3535
"""Determine the number of available blocks for the GPU KV cache and
3636
swappable CPU KV cache.
3737

0 commit comments

Comments
 (0)