65bf2ac165
This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend. It also refactors subquery_start_loc which was not refactored in the previous PR
13 lines
347 B
Python
13 lines
347 B
Python
from vllm.attention.backends.abstract import (AttentionBackend,
|
|
AttentionMetadata)
|
|
from vllm.attention.layer import Attention
|
|
from vllm.attention.selector import get_attn_backend
|
|
|
|
__all__ = [
|
|
"Attention",
|
|
"AttentionBackend",
|
|
"AttentionMetadata",
|
|
"Attention",
|
|
"get_attn_backend",
|
|
]
|