biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py (#32054)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-12 12:13:56 -05:00
committed by GitHub
parent 7c0d3c5152
commit 20228cb851
37 changed files with 374 additions and 370 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/v1/spec_decode/test_tree_attention.py
View File

@@ -12,9 +12,9 @@ from tests.v1.attention.utils import (
try_get_attention_backend,
)
from vllm.config import ParallelConfig, SpeculativeConfig
from vllm.v1.attention.backend import CommonAttentionMetadata
from vllm.v1.attention.backends.fa_utils import is_flash_attn_varlen_func_available
from vllm.v1.attention.backends.registry import AttentionBackendEnum
from vllm.v1.attention.backends.utils import CommonAttentionMetadata
if not is_flash_attn_varlen_func_available():
pytest.skip(