Unverified Commit 395aa823 authored by Woosuk Kwon's avatar Woosuk Kwon Committed by GitHub
Browse files

[Misc] Minor type annotation fix (#3716)

parent 26422e47
from functools import lru_cache from functools import lru_cache
from typing import Type
import torch import torch
...@@ -10,7 +11,7 @@ logger = init_logger(__name__) ...@@ -10,7 +11,7 @@ logger = init_logger(__name__)
@lru_cache(maxsize=None) @lru_cache(maxsize=None)
def get_attn_backend(dtype: torch.dtype) -> AttentionBackend: def get_attn_backend(dtype: torch.dtype) -> Type[AttentionBackend]:
if _can_use_flash_attn(dtype): if _can_use_flash_attn(dtype):
logger.info("Using FlashAttention backend.") logger.info("Using FlashAttention backend.")
from vllm.attention.backends.flash_attn import ( # noqa: F401 from vllm.attention.backends.flash_attn import ( # noqa: F401
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment