[Attention] Update attention imports (#29540)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -5,6 +5,7 @@ import functools
|
||||
import torch
|
||||
|
||||
from vllm.attention.backends.abstract import AttentionBackend, AttentionMetadata
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.selector import get_attn_backend
|
||||
from vllm.config import CacheConfig
|
||||
from vllm.config.vllm import VllmConfig
|
||||
@@ -22,8 +23,6 @@ from vllm.v1.kv_cache_interface import (
|
||||
KVCacheSpec,
|
||||
)
|
||||
|
||||
from ..layer import Attention
|
||||
|
||||
|
||||
@functools.lru_cache
|
||||
def create_chunked_local_attention_backend(
|
||||
|
||||
Reference in New Issue
Block a user