[3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py (#32054)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -15,14 +15,14 @@ from vllm.utils.math_utils import cdiv
|
||||
from vllm.utils.platform_utils import get_cu_count
|
||||
from vllm.v1.attention.backend import (
|
||||
AttentionBackend,
|
||||
AttentionCGSupport,
|
||||
AttentionImpl,
|
||||
AttentionMetadataBuilder,
|
||||
AttentionType,
|
||||
CommonAttentionMetadata,
|
||||
MultipleOf,
|
||||
)
|
||||
from vllm.v1.attention.backends.utils import (
|
||||
AttentionCGSupport,
|
||||
AttentionMetadataBuilder,
|
||||
CommonAttentionMetadata,
|
||||
split_decodes_prefills_and_extends,
|
||||
)
|
||||
from vllm.v1.attention.ops.merge_attn_states import merge_attn_states
|
||||
|
||||
Reference in New Issue
Block a user