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/e2e/test_async_spec_decode.py
View File

@@ -19,7 +19,7 @@ def sync_tracker():
Fixture that patches CommonAttentionMetadata.seq_lens_cpu to detect
lazy init syncs. Prints stack traces immediately when syncs occur.
"""
from vllm.v1.attention.backends.utils import CommonAttentionMetadata
from vllm.v1.attention.backend import CommonAttentionMetadata
# Shared counter for cross-process communication (inherited by fork)
sync_count = multiprocessing.Value("i", 0)