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

8
vllm/v1/attention/backends/triton_attn.py
View File

@@ -19,14 +19,12 @@ from vllm.platforms.interface import DeviceCapability
from vllm.utils.math_utils import next_power_of_2
from vllm.v1.attention.backend import (
AttentionBackend,
AttentionImpl,
AttentionType,
MultipleOf,
)
from vllm.v1.attention.backends.utils import (
AttentionCGSupport,
AttentionImpl,
AttentionMetadataBuilder,
AttentionType,
CommonAttentionMetadata,
MultipleOf,
)
from vllm.v1.attention.ops.triton_prefill_attention import context_attention_fwd
from vllm.v1.attention.ops.triton_reshape_and_cache_flash import (