[1/N][Attention] Restructure attention: move files (#31916)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -6,7 +6,6 @@ from itertools import islice
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.config import (
|
||||
CacheConfig,
|
||||
@@ -43,6 +42,7 @@ from vllm.model_executor.model_loader.weight_utils import (
|
||||
)
|
||||
from vllm.model_executor.models.utils import sequence_parallel_chunk
|
||||
from vllm.sequence import IntermediateTensors
|
||||
from vllm.v1.attention.backend import AttentionType
|
||||
|
||||
from .interfaces import MixtureOfExperts, SupportsPP
|
||||
from .utils import (
|
||||
|
||||
Reference in New Issue
Block a user